{"id":"https://openalex.org/W2063610885","doi":"https://doi.org/10.1145/2774959.2774965","title":"Fusing convolution kernels through tiling","display_name":"Fusing convolution kernels through tiling","publication_year":2015,"publication_date":"2015-06-08","ids":{"openalex":"https://openalex.org/W2063610885","doi":"https://doi.org/10.1145/2774959.2774965","mag":"2063610885"},"language":"en","primary_location":{"id":"doi:10.1145/2774959.2774965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2774959.2774965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023732985","display_name":"M. Ravishankar","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Mahesh Ravishankar","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072693649","display_name":"Paulius Micikevicius","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Paulius Micikevicius","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077691647","display_name":"Vinod Grover","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Vinod Grover","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5407,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74294607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8834511041641235},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.6796896457672119},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6130695939064026},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5849712491035461},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5823655724525452},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5183630585670471},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4902511239051819},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4590098261833191},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4111884534358978},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3231011927127838},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2701079845428467},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2601001262664795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8834511041641235},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.6796896457672119},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6130695939064026},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5849712491035461},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5823655724525452},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5183630585670471},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4902511239051819},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4590098261833191},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4111884534358978},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3231011927127838},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2701079845428467},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2601001262664795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2774959.2774965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2774959.2774965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1983317091","https://openalex.org/W2003798513","https://openalex.org/W2034761517","https://openalex.org/W2055312318","https://openalex.org/W2063656563","https://openalex.org/W2084917734","https://openalex.org/W2111308925","https://openalex.org/W2133352531","https://openalex.org/W2141280299","https://openalex.org/W2145023731","https://openalex.org/W2151764765","https://openalex.org/W2154078685","https://openalex.org/W2162569557","https://openalex.org/W2166906890"],"related_works":["https://openalex.org/W2885657154","https://openalex.org/W4289709346","https://openalex.org/W2119542776","https://openalex.org/W2014596857","https://openalex.org/W2582410692","https://openalex.org/W2140083133","https://openalex.org/W1485300234","https://openalex.org/W2258960507","https://openalex.org/W2097052821","https://openalex.org/W1981826665"],"abstract_inverted_index":{"Image":[0],"processing":[1],"pipelines":[2,22,94,180],"are":[3,62,102],"continuously":[4],"being":[5],"developed":[6],"to":[7,47,50,67,75,108,124,162],"deduce":[8],"more":[9,65],"information":[10],"about":[11],"objects":[12],"captured":[13],"in":[14,141],"images.":[15],"To":[16],"facilitate":[17],"the":[18,44,53,81,127,135,139,155,158,164,177,192],"development":[19],"of":[20,37,92,98,115,129,138,154,160,179,191],"such":[21,38,60],"several":[23],"Domain":[24],"Specific":[25],"Languages":[26],"(DSLs)":[27],"have":[28,74],"been":[29],"proposed":[30],"that":[31,83,101,150],"provide":[32],"constructs":[33],"for":[34],"easy":[35],"specification":[36,137],"computations.":[39],"It":[40],"is":[41,112],"then":[42],"upto":[43],"DSL":[45,131],"compiler":[46],"generate":[48],"code":[49,147],"efficiently":[51],"execute":[52],"pipeline":[54,140,156,196],"on":[55,168,187,199],"multiple":[56,152],"hardware":[57],"architectures.":[58],"While":[59],"compilers":[61],"getting":[63],"ever":[64],"sophisticated,":[66],"achieve":[68],"large":[69],"scale":[70],"adoption":[71],"these":[72,93],"DSLs":[73],"beat,":[76],"or":[77],"at":[78],"least":[79],"match,":[80],"performance":[82,178],"can":[84],"be":[85],"achieved":[86],"by":[87,185,197],"a":[88,96,130,146],"skilled":[89],"programmer.":[90],"Many":[91],"use":[95,114,159],"sequence":[97],"convolution":[99],"kernels":[100],"memory":[103,165],"bandwidth":[104,166],"bound.":[105],"One":[106],"way":[107],"address":[109],"this":[110,118,142,174],"bottleneck":[111],"through":[113,157],"tiling.":[116],"In":[117],"paper":[119],"we":[120,144],"describe":[121,145],"an":[122],"approach":[123],"tiling":[125,161],"within":[126],"context":[128],"called":[132],"Forma.":[133],"Using":[134,173],"high-level":[136],"DSL,":[143],"generation":[148],"algorithm":[149],"fuses":[151],"stages":[153],"reduce":[163],"requirements":[167],"both":[169],"GPU":[170],"and":[171,190],"CPU.":[172],"technique":[175],"improves":[176],"like":[181],"Canny":[182],"Edge":[183],"Detection":[184,195],"58%":[186],"NVIDIA":[188],"GPUs,":[189],"Harris":[193],"Corner":[194],"71%":[198],"CPUs.":[200]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}