{"id":"https://openalex.org/W2007516655","doi":"https://doi.org/10.1145/1854273.1854340","title":"Believe it or not!","display_name":"Believe it or not!","publication_year":2010,"publication_date":"2010-09-11","ids":{"openalex":"https://openalex.org/W2007516655","doi":"https://doi.org/10.1145/1854273.1854340","mag":"2007516655"},"language":"en","primary_location":{"id":"doi:10.1145/1854273.1854340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","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/A5035394281","display_name":"Rajesh Bordawekar","orcid":"https://orcid.org/0000-0002-8063-9220"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajesh Bordawekar","raw_affiliation_strings":["IBM T. J. Watson Research Center, Hawthorne, NY, USA","IBM Watson Research Center, Hawthorne, NY 10532, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Watson Research Center, Hawthorne, NY 10532, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025342111","display_name":"Uday Bondhugula","orcid":"https://orcid.org/0000-0002-8297-6159"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uday Bondhugula","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM Watson Research Center, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108533559","display_name":"Ravi Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Rao","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM Watson Research Center, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035394281"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":5.2434,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95942951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"538"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8471195697784424},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7841920256614685},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.6901980638504028},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6897096633911133},{"id":"https://openalex.org/keywords/posix-threads","display_name":"POSIX Threads","score":0.6702226400375366},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.62044757604599},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5755791664123535},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5503496527671814},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.42176997661590576},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3884931802749634},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3046383261680603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471195697784424},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7841920256614685},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.6901980638504028},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6897096633911133},{"id":"https://openalex.org/C41138395","wikidata":"https://www.wikidata.org/wiki/Q928112","display_name":"POSIX Threads","level":3,"score":0.6702226400375366},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.62044757604599},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5755791664123535},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5503496527671814},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.42176997661590576},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3884931802749634},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3046383261680603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1854273.1854340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1518474679","https://openalex.org/W1984005572","https://openalex.org/W2079834329","https://openalex.org/W2099404643","https://openalex.org/W2118031182","https://openalex.org/W2128249697","https://openalex.org/W2141170493","https://openalex.org/W2164585709","https://openalex.org/W2568842486"],"related_works":["https://openalex.org/W2899151995","https://openalex.org/W1507301366","https://openalex.org/W2962896931","https://openalex.org/W2887024010","https://openalex.org/W4378805959","https://openalex.org/W2122338824","https://openalex.org/W1542357320","https://openalex.org/W3198401590","https://openalex.org/W99177659","https://openalex.org/W2528421380"],"abstract_inverted_index":{"In":[0],"this":[1,28,112],"paper,":[2],"we":[3],"evaluate":[4],"performance":[5,110,167],"of":[6,111,168],"a":[7,14,19,23,31,74,121,152,158],"real-world":[8],"image":[9,21],"processing":[10],"application":[11,155],"that":[12],"uses":[13],"cross-correlation":[15],"algorithm":[16,29,113],"to":[17,161],"compare":[18],"given":[20],"with":[22,60],"reference":[24],"one.":[25],"We":[26],"implement":[27],"on":[30,79,95,114,157],"nVidia":[32,116],"GTX":[33,100],"285":[34,101],"GPU":[35,117,171],"using":[36,51],"CUDA,":[37],"and":[38,47,54,58,62,89,99,106,135],"also":[39],"parallelize":[40],"it":[41,148],"for":[42,68,85,151],"the":[43,69,80,96,115,166],"Intel":[44],"Xeon":[45],"(Nehalem)":[46],"IBM":[48],"Power7":[49],"processors,":[50],"both":[52],"manual":[53],"automatic":[55,86],"techniques.":[56],"Pthreads":[57],"OpenMP":[59],"SSE":[61],"VSX":[63],"vector":[64],"intrinsics":[65],"are":[66],"used":[67,84],"manually":[70],"parallelized":[71],"version,":[72],"while":[73],"state-of-the-art":[75],"optimization":[76],"framework":[77],"based":[78],"polyhedral":[81],"model":[82],"is":[83,149],"compiler":[87],"parallelization":[88],"optimization.":[90],"The":[91,109],"best":[92],"performing":[93],"versions":[94],"Power7,":[97],"Nehalem,":[98],"run":[102],"in":[103],"1.02s,":[104],"1.82s,":[105],"1.22s,":[107],"respectively.":[108],"suffers":[118],"from:":[119],"(1)":[120],"smaller":[122],"shared":[123],"memory,":[124],"(2)":[125],"unaligned":[126],"device":[127],"memory":[128],"access":[129],"patterns,":[130],"(3)":[131],"expensive":[132],"atomic":[133],"operations,":[134],"(4)":[136],"weaker":[137],"single-thread":[138],"performance.":[139],"These":[140],"results":[141],"conclusively":[142],"demonstrate":[143],"that,":[144],"under":[145],"certain":[146],"conditions,":[147],"possible":[150],"FLOP-intensive":[153],"structured":[154],"running":[156],"multi-core":[159],"processor":[160],"match":[162],"or":[163],"even":[164],"beat":[165],"an":[169],"equivalent":[170],"version.":[172]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
