{"id":"https://openalex.org/W2397150565","doi":"https://doi.org/10.3233/978-1-60750-803-8-65","title":"Fast Heterogeneous Computing: Principles and CUDA Programming","display_name":"Fast Heterogeneous Computing: Principles and CUDA Programming","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2397150565","doi":"https://doi.org/10.3233/978-1-60750-803-8-65","mag":"2397150565"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-60750-803-8-65","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-803-8-65","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5091119982","display_name":"Janusz S. Kowalik","orcid":"https://orcid.org/0009-0007-1743-3653"},"institutions":[{"id":"https://openalex.org/I40413290","display_name":"University of Gda\u0144sk","ror":"https://ror.org/011dv8m48","country_code":"PL","type":"education","lineage":["https://openalex.org/I40413290"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Kowalik Janusz","raw_affiliation_strings":["University of Gda\u0144sk, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Gda\u0144sk, Gdansk, Poland","institution_ids":["https://openalex.org/I40413290"]}]},{"author_position":"last","author":{"id":null,"display_name":"Arłukowicz Piotr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arłukowicz Piotr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091119982"],"corresponding_institution_ids":["https://openalex.org/I40413290"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29811575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9232000112533569,"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":0.9232000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9315745234489441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7029294967651367},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.657983660697937},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4630797803401947},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4472624659538269},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17098090052604675},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.06130000948905945}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9315745234489441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7029294967651367},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.657983660697937},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4630797803401947},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4472624659538269},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17098090052604675},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.06130000948905945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-60750-803-8-65","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-803-8-65","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2005148983","https://openalex.org/W2792081825"],"abstract_inverted_index":{"The":[0,44,65,111],"current":[1],"dynamic":[2],"development":[3],"of":[4,24,29,35,51,59,73,103,128,159,164],"heterogeneous":[5],"(CPU+GPU)":[6],"computing":[7,31],"and":[8,14,37,53,93,106],"its":[9],"applications":[10],"to":[11,20,56,122,170],"scientific,":[12],"engineering":[13],"business":[15],"problems":[16],"owes":[17],"the":[18,27,47,71,104,165],"success":[19],"several":[21],"factors.":[22],"One":[23],"them":[25,60],"is":[26,46,70,113],"maturity":[28],"parallel":[30,41,91],"after":[32],"many":[33,58,75],"years":[34],"struggle":[36],"experimentation":[38],"with":[39],"different":[40],"computer":[42],"architectures.":[43],"second":[45],"relatively":[48],"low":[49],"price":[50],"processors":[52],"our":[54],"ability":[55],"put":[57],"on":[61,131],"a":[62,124],"single":[63],"chip.":[64],"third":[66],"equally":[67],"important":[68],"factor":[69],"structure":[72],"very":[74],"numerical":[76],"mathematics":[77],"algorithms":[78],"containing":[79],"highly":[80],"parallelizable":[81],"operations":[82],"whose":[83],"processing":[84],"can":[85],"be":[86],"accelerated":[87],"by":[88],"using":[89],"massively":[90],"GPU":[92],"multicore":[94],"CPU.":[95],"In":[96],"this":[97],"paper":[98,112],"we":[99,156],"provide":[100],"an":[101],"overview":[102],"field":[105],"simple":[107,125],"but":[108],"realistic":[109],"examples.":[110],"targeted":[114],"for":[115],"beginner":[116],"CUDA":[117,139],"users.":[118],"We":[119],"have":[120],"decided":[121],"show":[123],"source":[126],"code":[127],"vector":[129],"addition":[130],"GPU.":[132],"This":[133],"example":[134],"does":[135],"not":[136],"cover":[137],"advanced":[138],"usage,":[140],"such":[141],"as":[142],"shared":[143],"memory":[144],"accesses,":[145],"divergent":[146],"branches,":[147],"optimization":[148,166],"coalescing":[149],"or":[150],"loop":[151],"unrolling.":[152],"To":[153],"illustrate":[154],"performance":[155],"demonstrate":[157],"results":[158],"matrix-matrix":[160],"multiplication":[161],"where":[162],"some":[163],"techniques":[167],"were":[168],"used":[169],"gain":[171],"impressive":[172],"speedup.":[173]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2016-06-24T00:00:00"}