{"id":"https://openalex.org/W4411350482","doi":"https://doi.org/10.1145/3744909","title":"3D GNLM: Efficient 3D Non-Local Means Kernel with Nested Reuse Strategies for Embedded GPUs","display_name":"3D GNLM: Efficient 3D Non-Local Means Kernel with Nested Reuse Strategies for Embedded GPUs","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411350482","doi":"https://doi.org/10.1145/3744909"},"language":"en","primary_location":{"id":"doi:10.1145/3744909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744909","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3744909","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100636346","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0001-6933-6491"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Nanjing University","Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011965834","display_name":"Qiong Chang","orcid":"https://orcid.org/0000-0002-4447-0480"},"institutions":[{"id":"https://openalex.org/I4210085920","display_name":"Shanghai Institute for Science of Science","ror":"https://ror.org/004srxn73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210085920"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiong Chang","raw_affiliation_strings":["School of Computing, Institute of Science Tokyo","School of Computing, Institute of Science Tokyo, Meguro, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computing, Institute of Science Tokyo","institution_ids":["https://openalex.org/I4210085920","https://openalex.org/I4400009020"]},{"raw_affiliation_string":"School of Computing, Institute of Science Tokyo, Meguro, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395668","display_name":"Yun Li","orcid":"https://orcid.org/0000-0003-1753-7317"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Li","raw_affiliation_strings":["Nanjing University","Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026559426","display_name":"Jun Miyazaki","orcid":"https://orcid.org/0000-0002-3038-7678"},"institutions":[{"id":"https://openalex.org/I4210085920","display_name":"Shanghai Institute for Science of Science","ror":"https://ror.org/004srxn73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210085920"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Miyazaki","raw_affiliation_strings":["School of Computing, Institute of Science Tokyo","School of Computing, Institute of Science Tokyo, Meguro, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computing, Institute of Science Tokyo","institution_ids":["https://openalex.org/I4210085920","https://openalex.org/I4400009020"]},{"raw_affiliation_string":"School of Computing, Institute of Science Tokyo, Meguro, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100636346"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11638071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","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/T10688","display_name":"Image and Signal Denoising Methods","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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9957000017166138,"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":0.8175545930862427},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.63026362657547},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6127225160598755},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5248858332633972},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3656008839607239},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33322834968566895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175545930862427},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.63026362657547},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6127225160598755},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5248858332633972},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3656008839607239},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33322834968566895},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3744909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744909","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50735820","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100934322","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/3744909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744909","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2030648715","https://openalex.org/W2041625018","https://openalex.org/W2097073572","https://openalex.org/W2137901785","https://openalex.org/W2142592339","https://openalex.org/W2237473774","https://openalex.org/W2267520283","https://openalex.org/W2294228199","https://openalex.org/W2339758283","https://openalex.org/W2489899240","https://openalex.org/W2793775504","https://openalex.org/W2901821416","https://openalex.org/W2963091558","https://openalex.org/W2972158684","https://openalex.org/W3000106890","https://openalex.org/W3004947139","https://openalex.org/W3013302728","https://openalex.org/W3027451255","https://openalex.org/W3035006120","https://openalex.org/W3047011367","https://openalex.org/W3102259464","https://openalex.org/W3104467360","https://openalex.org/W3110460200","https://openalex.org/W3166036439","https://openalex.org/W4214742436","https://openalex.org/W4224444092","https://openalex.org/W4285697865","https://openalex.org/W4310024031","https://openalex.org/W4328053402","https://openalex.org/W4386374621","https://openalex.org/W4401818004","https://openalex.org/W4410321819"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2353602216","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W1910583078","https://openalex.org/W2351618306","https://openalex.org/W2999162218","https://openalex.org/W1537443268","https://openalex.org/W2390634956"],"abstract_inverted_index":{"The":[0,48,121],"3D":[1,13,49,69,83,224],"Non-Local":[2],"Means":[3],"(NLM)":[4],"algorithm":[5,51],"has":[6,28],"become":[7],"a":[8,68,156,181,221],"crucial":[9],"preprocessing":[10],"technique":[11],"for":[12,56,135,152,177],"image":[14,225],"datasets":[15,226],"due":[16],"to":[17,31,114,128,144,167,196,228],"its":[18],"effectiveness":[19],"in":[20,35,93,132],"denoising":[21],"while":[22],"preserving":[23],"fine":[24],"details.":[25],"This":[26],"method":[27],"been":[29],"proven":[30],"be":[32],"highly":[33],"efficient":[34,110],"high-demand":[36],"tasks":[37],"within":[38,67],"industrial":[39],"applications":[40],"such":[41],"as":[42,164],"medical":[43],"imaging":[44],"and":[45,100,118,169,176,192],"remote":[46],"sensing.":[47],"NLM":[50],"computes":[52],"the":[53,61,73,78,87,139,214],"filtered":[54,174],"value":[55],"each":[57],"voxel":[58],"by":[59,77],"calculating":[60],"weighted":[62],"average":[63,209],"of":[64,82,211,223],"all":[65],"voxels":[66],"search":[70],"window,":[71],"where":[72],"weights":[74],"are":[75],"determined":[76],"similarity":[79,171],"between":[80,173],"pairs":[81],"template":[84],"windows.":[85],"Therefore,":[86],"computational":[88,98],"burden":[89],"becomes":[90],"significant,":[91],"especially":[92],"embedded":[94,215],"GPUs":[95],"with":[96],"limited":[97],"power":[99],"memory":[101,119,163],"resources.":[102],"To":[103],"address":[104],"this":[105],"issue,":[106],"we":[107,137,154,179],"propose":[108],"an":[109,165,208],"GPU":[111,161],"parallel":[112],"kernel":[113,122,206],"minimize":[115],"redundant":[116,130],"computations":[117,131],"accesses.":[120],"integrates":[123],"three":[124,133],"nested":[125],"reuse":[126,145,170],"strategies":[127],"handle":[129],"dimensions:":[134],"columns,":[136],"leverage":[138],"fast":[140],"data":[141],"exchange":[142],"mechanism":[143],"column":[146],"computation":[147,188,199],"results":[148,202],"via":[149],"on-chip":[150,194],"registers;":[151],"rows,":[153],"use":[155],"sliding":[157],"window":[158],"strategy,":[159],"utilizing":[160],"global":[162],"intermediary":[166],"store":[168],"values":[172],"rows;":[175],"channels,":[178],"introduce":[180],"zigzag":[182],"scanning":[183],"strategy":[184],"that":[185,204],"enables":[186],"simultaneous":[187],"across":[189,220],"multiple":[190],"channels":[191],"employs":[193],"registers":[195],"facilitate":[197],"channel":[198],"reuse.":[200],"Experimental":[201],"demonstrate":[203],"our":[205],"achieves":[207],"speedup":[210],"7.7x":[212],"on":[213],"Jetson":[216],"AGX":[217],"Xavier":[218],"platform":[219],"range":[222],"compared":[227],"existing":[229],"methods,":[230],"showcasing":[231],"exceptional":[232],"performance.":[233]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}