{"id":"https://openalex.org/W2084701848","doi":"https://doi.org/10.1145/2668904.2668941","title":"Optimizing large scale CUDA applications using input data specific optimizations","display_name":"Optimizing large scale CUDA applications using input data specific optimizations","publication_year":2014,"publication_date":"2014-11-13","ids":{"openalex":"https://openalex.org/W2084701848","doi":"https://doi.org/10.1145/2668904.2668941","mag":"2084701848"},"language":"en","primary_location":{"id":"doi:10.1145/2668904.2668941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2668904.2668941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th European Conference on Visual Media Production","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/A5004908355","display_name":"Blagovest Taskov","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Blagovest Taskov","raw_affiliation_strings":["Chaos Group"],"affiliations":[{"raw_affiliation_string":"Chaos Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004908355"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13854887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":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":0.9993000030517578,"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":0.9986000061035156,"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/cuda","display_name":"CUDA","score":0.9339966773986816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8591535091400146},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7829943299293518},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6549391150474548},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6257351636886597},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5640201568603516},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.5112819671630859},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.49828076362609863},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4587263762950897},{"id":"https://openalex.org/keywords/powerpc","display_name":"PowerPC","score":0.4316246509552002},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4297168254852295},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4126589000225067},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32442474365234375},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2629126012325287},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.20892095565795898},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1798062026500702},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14414674043655396}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9339966773986816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591535091400146},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7829943299293518},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6549391150474548},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6257351636886597},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5640201568603516},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.5112819671630859},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.49828076362609863},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4587263762950897},{"id":"https://openalex.org/C56005371","wikidata":"https://www.wikidata.org/wiki/Q209860","display_name":"PowerPC","level":3,"score":0.4316246509552002},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4297168254852295},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4126589000225067},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32442474365234375},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2629126012325287},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.20892095565795898},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1798062026500702},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14414674043655396},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2668904.2668941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2668904.2668941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th European Conference on Visual Media Production","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W1762731526","https://openalex.org/W2030089573","https://openalex.org/W2159054268"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2184274109","https://openalex.org/W2364044215","https://openalex.org/W1522250664","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112"],"abstract_inverted_index":{"CUDA":[0,38,104],"applications":[1],"and":[2,28,39,59,70,83,170],"general-purpose":[3],"GPU":[4,42,147],"(GPGPU)":[5],"programs":[6],"are":[7,31,153,163,172],"widely":[8],"used":[9,184],"nowadays":[10],"for":[11,130],"solving":[12],"computationally":[13],"intensive":[14],"tasks.":[15],"There":[16],"is":[17,86,124],"a":[18,56,61,128,142],"substantial":[19],"effort":[20],"in":[21,157,189],"the":[22,48,68,101,103,113,133,146,164,187,193,202],"form":[23],"of":[24,64,109,111,132,195],"tools,":[25],"papers,":[26],"books":[27],"features":[29],"that":[30,181],"targeted":[32],"at":[33],"GPGPU":[34,73],"APIs":[35],"such":[36,76],"as":[37,77],"OpenCL.":[40],"The":[41],"architecture,":[43],"being":[44],"substantially":[45],"different":[46,57,62],"from":[47,67,97],"traditional":[49,69],"CPU":[50],"ones":[51],"(x86,":[52],"PowerPC,":[53],"ARM)":[54],"requires":[55],"approach":[58,180],"introduces":[60],"set":[63],"challenges.":[65],"Apart":[66],"well":[71,93],"examined":[72],"problems":[74],"-":[75,96],"memory":[78],"access":[79],"patterns,":[80],"parallel":[81],"designs":[82],"occupancy,":[84],"there":[85],"yet":[87],"another":[88],"really":[89],"important,":[90],"but":[91,137],"not":[92],"studied":[94],"setback":[95],"one":[98,176],"point":[99],"onward,":[100],"bigger":[102],"application":[105],"gets":[106],"(in":[107],"terms":[108],"lines":[110],"code)":[112],"slower":[114],"it":[115,138],"becomes,":[116],"mostly":[117],"due":[118,148],"to":[119,149,155,167,174,185],"register":[120],"spilling.":[121],"Register":[122],"spilling":[123],"more":[125],"or":[126],"less":[127],"problem":[129],"most":[131],"available":[134],"architectures":[135],"today,":[136],"can":[139],"easily":[140],"become":[141],"massive":[143],"bottleneck":[144],"on":[145,201],"its":[150],"nature.":[151],"We":[152],"going":[154,173],"examine":[156],"detail":[158],"why":[159],"this":[160,196],"happens,":[161],"what":[162],"common":[165],"ways":[166],"solve":[168],"it,":[169],"we":[171,198],"propose":[175],"simple,":[177],"presently":[178],"undocumented":[179],"may":[182],"be":[183],"alleviate":[186],"issue":[188],"some":[190],"situations.":[191],"For":[192],"purpose":[194],"paper":[197],"will":[199],"focus":[200],"NVidia":[203],"Fermi":[204],"Architecture":[205]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}