{"id":"https://openalex.org/W3006830071","doi":"https://doi.org/10.1145/3366428.3380773","title":"Unveiling kernel concurrency in multiresolution filters on GPUs with an image processing DSL","display_name":"Unveiling kernel concurrency in multiresolution filters on GPUs with an image processing DSL","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3006830071","doi":"https://doi.org/10.1145/3366428.3380773","mag":"3006830071"},"language":"en","primary_location":{"id":"doi:10.1145/3366428.3380773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366428.3380773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit","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/A5035954398","display_name":"Bo Qiao","orcid":"https://orcid.org/0000-0001-9644-0577"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bo Qiao","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051274212","display_name":"Oliver Reiche","orcid":"https://orcid.org/0000-0002-5125-4508"},"institutions":[{"id":"https://openalex.org/I4210153902","display_name":"Siemens Healthcare (Germany)","ror":"https://ror.org/0449c4c15","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210153902"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Reiche","raw_affiliation_strings":["Siemens Healthineers AG, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Siemens Healthineers AG, Erlangen, Germany","institution_ids":["https://openalex.org/I4210153902"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076672029","display_name":"J\u00fcrgen Teich","orcid":"https://orcid.org/0000-0001-6285-5862"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Teich","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072039340","display_name":"Frank Hannig","orcid":"https://orcid.org/0000-0003-3663-6484"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Hannig","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035954398"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.3908,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59867581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9973999857902527,"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":0.9958000183105469,"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":0.8485260605812073},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7474361658096313},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.659103512763977},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.648686945438385},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6235832571983337},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5966298580169678},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.5918121337890625},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5497956871986389},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.4998900890350342},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4704282283782959},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33623185753822327},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32571572065353394},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22990494966506958},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1407749354839325},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.14024990797042847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485260605812073},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7474361658096313},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.659103512763977},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.648686945438385},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6235832571983337},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5966298580169678},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.5918121337890625},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5497956871986389},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.4998900890350342},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4704282283782959},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33623185753822327},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32571572065353394},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22990494966506958},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1407749354839325},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.14024990797042847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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:10.1145/3366428.3380773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366428.3380773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W564060940","https://openalex.org/W1622620102","https://openalex.org/W1972072725","https://openalex.org/W1972612668","https://openalex.org/W1989988531","https://openalex.org/W1994001225","https://openalex.org/W1994235817","https://openalex.org/W2016705856","https://openalex.org/W2028525469","https://openalex.org/W2075745057","https://openalex.org/W2084917734","https://openalex.org/W2098274770","https://openalex.org/W2099244020","https://openalex.org/W2100925004","https://openalex.org/W2103504761","https://openalex.org/W2152517358","https://openalex.org/W2153709524","https://openalex.org/W2323693848","https://openalex.org/W2605178034","https://openalex.org/W2619616493","https://openalex.org/W2753191874","https://openalex.org/W2808498336","https://openalex.org/W2952562588","https://openalex.org/W2982826349","https://openalex.org/W4239881334","https://openalex.org/W4243035950","https://openalex.org/W4244917406","https://openalex.org/W6602938371"],"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/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Multiresolution":[0],"filters,":[1],"analyzing":[2],"information":[3],"at":[4,22],"different":[5,17],"scales,":[6],"are":[7],"crucial":[8],"for":[9,76,134],"many":[10],"applications":[11,137],"in":[12,25,64],"digital":[13],"image":[14,117],"processing.":[15],"The":[16,141],"space":[18],"and":[19,89,99,129,174],"time":[20],"complexity":[21],"distinct":[23],"scales":[24],"the":[26,58,96,131,158,169,179],"unique":[27],"pyramidal":[28],"structure":[29],"poses":[30],"a":[31,68,73,93,112,149],"challenge":[32],"as":[33,35,44,80,83],"well":[34,81],"an":[36,47,116],"opportunity":[37],"to":[38,127,155,166,176],"implementations":[39],"on":[40,105,138],"modern":[41],"accelerators":[42],"such":[43],"GPUs":[45,107],"with":[46],"increasing":[48],"number":[49],"of":[50,60,79,153],"compute":[51],"units.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,71],"exploit":[57],"potential":[59],"concurrent":[61],"kernel":[62],"execution":[63],"multiresolution":[65],"filters.":[66],"As":[67,92],"major":[69],"contribution,":[70,95],"present":[72],"model-based":[74],"approach":[75,114,126],"performance":[77,133],"analysis":[78],"single-":[82],"multi-stream":[84],"implementations,":[85],"combining":[86],"both":[87],"application-":[88],"architecture-specific":[90],"knowledge.":[91],"second":[94],"involved":[97],"transformations":[98],"code":[100],"generators":[101],"using":[102,115],"CUDA":[103,184],"streams":[104],"Nvidia":[106],"have":[108],"been":[109],"integrated":[110],"into":[111],"compiler-based":[113],"processing":[118],"DSL":[119,172],"called":[120],"Hipacc.":[121],"We":[122],"then":[123],"apply":[124],"our":[125,145,163],"evaluate":[128],"compare":[130],"achieved":[132],"four":[135],"real-world":[136],"three":[139],"GPUs.":[140],"results":[142],"show":[143],"that":[144],"method":[146],"can":[147],"achieve":[148],"geometric":[150],"mean":[151],"speedup":[152],"up":[154,165,175],"2.5":[156],"over":[157,168,178],"original":[159],"Hipacc":[160],"implementation":[161],"without":[162],"approach,":[164],"2.0":[167],"other":[170],"state-of-the-art":[171],"Halide,":[173],"1.3":[177],"recently":[180],"released":[181],"programming":[182],"model":[183],"Graph":[185],"from":[186],"Nvidia.":[187]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}