{"id":"https://openalex.org/W2162289995","doi":"https://doi.org/10.1109/cgo.2007.13","title":"GPU Computing: Programming a Massively Parallel Processor","display_name":"GPU Computing: Programming a Massively Parallel Processor","alternate_titles":[],"publication_year":2007,"publication_date":"2007-03-01","ids":{"openalex":"https://openalex.org/W2162289995","doi":"https://doi.org/10.1109/cgo.2007.13","mag":"2162289995"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2007.13","doi":"https://doi.org/10.1109/cgo.2007.13","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2007.13","pdf_url":null,"source":{"id":"https://openalex.org/S4393918247","display_name":"Proceedings of the CGO/Proceedings of the ... CGO","issn_l":"2164-2397","issn":["2164-2397"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization (CGO'07)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2162289995"],"child_works_count":0,"type":"conference-abstract","is_traditional":false,"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/A5020493351","display_name":"Ian Buck","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Ian Buck","raw_affiliation_strings":["GPU-Compute Software Manager, NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GPU-Compute Software Manager, NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020493351"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"17"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":9.999999747378752e-05,"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/gpu-computing","display_name":"GPU computing","score":0.9980000257492065},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9860000014305115},{"id":"https://openalex.org/keywords/massively-parallel-computers","display_name":"massively parallel computers","score":0.8529999852180481},{"id":"https://openalex.org/keywords/parallel-programming","display_name":"parallel programming","score":0.6679999828338623},{"id":"https://openalex.org/keywords/parallel-program-compilation","display_name":"parallel program compilation","score":0.6549999713897705},{"id":"https://openalex.org/keywords/compute-intensive-applications","display_name":"compute-intensive applications","score":0.746999979019165},{"id":"https://openalex.org/keywords/cpu-vs-gpu-performance-comparison","display_name":"CPU vs GPU performance comparison","score":0.6679999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596820831298828},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8283151388168335},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.7607511878013611},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7393159866333008},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6825761795043945},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6372025609016418},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.560619592666626},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5018179416656494},{"id":"https://openalex.org/C177681979","wikidata":"https://www.wikidata.org/wiki/Q633182","display_name":"Shader","level":3,"score":0.4756184220314026},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42554157972335815},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.4227392077445984},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.335548996925354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19115716218948364},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15836885571479797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2007.13","doi":"https://doi.org/10.1109/cgo.2007.13","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2007.13","pdf_url":null,"source":{"id":"https://openalex.org/S4393918247","display_name":"Proceedings of the CGO/Proceedings of the ... CGO","issn_l":"2164-2397","issn":["2164-2397"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization (CGO'07)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2808569185","https://openalex.org/W2340937903","https://openalex.org/W1982825626","https://openalex.org/W7100617811","https://openalex.org/W1995144992","https://openalex.org/W2364044215","https://openalex.org/W2034050544","https://openalex.org/W1971587460","https://openalex.org/W2120249721","https://openalex.org/W6980013681"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Many":[4],"researchers":[5],"have":[6],"observed":[7],"that":[8,104],"general":[9],"purpose":[10],"computing":[11,61,69,83],"with":[12,62],"programmable":[13],"graphics":[14,47,159],"hardware":[15],"(GPUs)":[16],"has":[17,39],"shown":[18],"promise":[19],"to":[20,54,68,80,111],"solve":[21,81,112,141],"many":[22,29],"of":[23,31,45,72,137],"the":[24,34,43,86,97,107,147,156],"world's":[25],"compute":[26,142],"intensive":[27,143],"problems,":[28,84],"orders":[30],"magnitude":[32],"faster":[33],"conventional":[35],"CPUs.":[36],"The":[37,93],"challenge":[38],"been":[40],"working":[41],"within":[42],"constraints":[44],"a":[46,65,89,100,135],"programming":[48],"environment":[49,103],"and":[50,78,126,145],"limited":[51],"language":[52],"support":[53],"leverage":[55],"this":[56,130],"huge":[57],"performance":[58],"potential.":[59],"GPU":[60,87,98],"CUDA":[63,139,162],"is":[64],"new":[66,113],"approach":[67],"where":[70],"hundreds":[71],"on-chip":[73],"processor":[74],"cores":[75],"simultaneously":[76],"communicate":[77],"cooperate":[79],"complex":[82],"transforming":[85],"into":[88],"massively":[90],"parallel":[91,151],"processor.":[92],"NVIDIA":[94],"C-compiler":[95],"for":[96,153],"provides":[99],"complete":[101],"development":[102],"gives":[105],"developers":[106],"tools":[108],"they":[109],"need":[110],"problems":[114,144],"in":[115],"computation-intensive":[116],"applications":[117,163],"such":[118],"as":[119],"product":[120],"design,":[121],"data":[122],"analysis,":[123],"technical":[124],"computing,":[125],"game":[127],"physics.":[128],"In":[129],"talk,":[131],"I":[132],"will":[133],"provide":[134],"description":[136],"how":[138],"can":[140],"highlight":[146],"challenges":[148],"when":[149],"compiling":[150],"programs":[152],"GPUs":[154],"including":[155],"differences":[157],"between":[158],"shaders":[160],"vs.":[161]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2162289995","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2016-06-24T00:00:00"}
