{"id":"https://openalex.org/W2615663338","doi":"https://doi.org/10.1145/3204919.3204924","title":"CLBlast","display_name":"CLBlast","publication_year":2018,"publication_date":"2018-05-02","ids":{"openalex":"https://openalex.org/W2615663338","doi":"https://doi.org/10.1145/3204919.3204924","mag":"2615663338"},"language":"en","primary_location":{"id":"doi:10.1145/3204919.3204924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3204924","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.05249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cedric Nugteren","orcid":null},"institutions":[{"id":"https://openalex.org/I2905213637","display_name":"TomTom (Netherlands)","ror":"https://ror.org/04as6y835","country_code":"NL","type":"company","lineage":["https://openalex.org/I2905213637"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Cedric Nugteren","raw_affiliation_strings":["TomTom, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"TomTom, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I2905213637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2905213637"],"apc_list":null,"apc_paid":null,"fwci":6.0526,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96850668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9937999844551086,"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/variety","display_name":"Variety (cybernetics)","score":0.6823999881744385},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5527999997138977},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.4350999891757965},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.38960000872612},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.35899999737739563},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449000120162964},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6823999881744385},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5073999762535095},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4016000032424927},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C2986422732","wikidata":"https://www.wikidata.org/wiki/Q753025","display_name":"Auto tuning","level":4,"score":0.2800999879837036},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3204919.3204924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3204924","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"},{"id":"pmh:oai:arXiv.org:1705.05249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05249","pdf_url":"https://arxiv.org/pdf/1705.05249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.05249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05249","pdf_url":"https://arxiv.org/pdf/1705.05249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1790519466","https://openalex.org/W1863336885","https://openalex.org/W2038509324","https://openalex.org/W2059745360","https://openalex.org/W2062368747","https://openalex.org/W2093843662","https://openalex.org/W2110108576","https://openalex.org/W2262336012","https://openalex.org/W2499931820","https://openalex.org/W2531348778","https://openalex.org/W2613143750","https://openalex.org/W2623579764","https://openalex.org/W2964301839"],"related_works":[],"abstract_inverted_index":{"This":[0,143],"work":[1],"introduces":[2],"CLBlast,":[3],"an":[4,123],"open-source":[5],"BLAS":[6,66],"library":[7,147],"providing":[8],"optimized":[9,71],"OpenCL":[10,65,80,163],"routines":[11],"to":[12,40],"accelerate":[13,41],"dense":[14],"linear":[15],"algebra":[16],"for":[17,72,99,155],"a":[18,35,76,135,159],"wide":[19,160],"variety":[20,78,161],"of":[21,44,79,152,162],"devices.":[22],"It":[23],"is":[24,70],"targeted":[25],"at":[26],"machine":[27],"learning":[28],"and":[29,32,73,90,118,128,148],"HPC":[30],"applications":[31,46],"thus":[33],"provides":[34],"fast":[36],"matrix-multiplication":[37],"routine":[38],"(GEMM)":[39],"the":[42,146,150],"core":[43],"many":[45],"(e.g.":[47],"deep":[48],"learning,":[49],"iterative":[50],"solvers,":[51],"astrophysics,":[52],"computational":[53],"fluid":[54],"dynamics,":[55],"quantum":[56],"chemistry).":[57],"CLBlast":[58,153],"has":[59,122],"five":[60],"main":[61],"advantages":[62,151],"over":[63],"other":[64],"libraries:":[67],"1)":[68],"it":[69,94,107,121,129],"tested":[74],"on":[75,102,158],"large":[77],"devices":[81,86],"including":[82],"less":[83],"commonly":[84],"used":[85],"such":[87],"as":[88],"embedded":[89],"low-power":[91],"GPUs,":[92],"2)":[93],"can":[95,108,130],"be":[96],"explicitly":[97],"tuned":[98],"specific":[100,103],"problem-sizes":[101],"hardware":[104],"platforms,":[105],"3)":[106],"perform":[109],"operations":[110,133],"in":[111,134],"half-precision":[112],"floating-point":[113],"FP16":[114],"saving":[115],"bandwidth,":[116],"time":[117],"energy,":[119],"4)":[120],"optional":[124],"CUDA":[125],"back-end,":[126],"5)":[127],"combine":[131],"multiple":[132],"single":[136],"batched":[137],"routine,":[138],"accelerating":[139],"smaller":[140],"problems":[141],"significantly.":[142],"paper":[144],"describes":[145],"demonstrates":[149],"experimentally":[154],"different":[156],"use-cases":[157],"hardware.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-05-26T00:00:00"}