{"id":"https://openalex.org/W2326144501","doi":"https://doi.org/10.1109/tpds.2016.2536028","title":"A Fast Discrete Wavelet Transform Using Hybrid Parallelism on GPUs","display_name":"A Fast Discrete Wavelet Transform Using Hybrid Parallelism on GPUs","publication_year":2016,"publication_date":"2016-02-29","ids":{"openalex":"https://openalex.org/W2326144501","doi":"https://doi.org/10.1109/tpds.2016.2536028","mag":"2326144501"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2536028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2536028","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5055052124","display_name":"Tran Minh Quan","orcid":"https://orcid.org/0000-0001-7374-9168"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tran Minh Quan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025485089","display_name":"Won\u2010Ki Jeong","orcid":"https://orcid.org/0000-0002-9393-6451"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won-Ki Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055052124"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":1.336,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8635105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":"11","first_page":"3088","last_page":"3100"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994000196456909,"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":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8609156608581543},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7302130460739136},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.6841599345207214},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.6297930479049683},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5111783146858215},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45647674798965454},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.40717318654060364},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.340992271900177},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.32780593633651733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24377676844596863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8609156608581543},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7302130460739136},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.6841599345207214},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.6297930479049683},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5111783146858215},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45647674798965454},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.40717318654060364},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.340992271900177},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.32780593633651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24377676844596863}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2016.2536028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2536028","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/20725","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/document/7422119/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ARTICLE"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3059998808","display_name":null,"funder_award_id":"10054548","funder_id":"https://openalex.org/F4320334879","funder_display_name":"Korea Evaluation Institute of Industrial Technology"},{"id":"https://openalex.org/G5299042602","display_name":null,"funder_award_id":"NRF-2014R1A1A2058773","funder_id":"https://openalex.org/F4320321408","funder_display_name":"Ministry of Education"},{"id":"https://openalex.org/G8699085713","display_name":null,"funder_award_id":"R0190-15-2012","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320309788","display_name":"Neurosciences Research Foundation","ror":"https://ror.org/05exfab56"},{"id":"https://openalex.org/F4320310050","display_name":"University of Utah","ror":"https://ror.org/03r0ha626"},{"id":"https://openalex.org/F4320321348","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W18046889","https://openalex.org/W1988227609","https://openalex.org/W1995100236","https://openalex.org/W1995642220","https://openalex.org/W2020919250","https://openalex.org/W2029816571","https://openalex.org/W2039441033","https://openalex.org/W2047181014","https://openalex.org/W2053961604","https://openalex.org/W2058929932","https://openalex.org/W2061171222","https://openalex.org/W2063186542","https://openalex.org/W2068798641","https://openalex.org/W2077917848","https://openalex.org/W2092696828","https://openalex.org/W2099563019","https://openalex.org/W2113190809","https://openalex.org/W2113197522","https://openalex.org/W2115755118","https://openalex.org/W2131274487","https://openalex.org/W2132984323","https://openalex.org/W2141084005","https://openalex.org/W2148414385","https://openalex.org/W2152328854","https://openalex.org/W2161907987","https://openalex.org/W2782405879","https://openalex.org/W3141650078","https://openalex.org/W4255272544","https://openalex.org/W7017254688"],"related_works":["https://openalex.org/W3145240193","https://openalex.org/W2540373069","https://openalex.org/W2503137108","https://openalex.org/W2119534391","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2062253548","https://openalex.org/W2393490604","https://openalex.org/W2393707426","https://openalex.org/W2147073383"],"abstract_inverted_index":{"Wavelet":[0],"transform":[1,58,131],"has":[2,43],"been":[3,61],"widely":[4],"used":[5],"in":[6,86,136,176],"many":[7,28,52],"signal":[8,26],"and":[9,24,51,98,100,105,173,193],"image":[10],"processing":[11,40],"applications.":[12],"Due":[13],"to":[14,111],"its":[15,115],"wide":[16],"adoption":[17],"for":[18,47,126],"time-critical":[19],"applications,":[20],"such":[21,89],"as":[22,90],"streaming":[23],"real-time":[25],"processing,":[27],"acceleration":[29],"techniques":[30],"were":[31],"developed":[32],"during":[33],"the":[34,38,71,74,159,182],"past":[35],"decade.":[36],"Recently,":[37],"graphics":[39],"unit":[41],"(GPU)":[42],"gained":[44],"much":[45],"attention":[46],"accelerating":[48],"computationally-intensive":[49],"problems":[50],"solutions":[53],"of":[54,65,73,184],"GPU-based":[55],"discrete":[56],"wavelet":[57],"(DWT)":[59],"have":[60],"introduced,":[62],"but":[63],"most":[64],"them":[66],"did":[67],"not":[68],"fully":[69],"leverage":[70],"potential":[72],"GPU.":[75],"In":[76,117],"this":[77],"paper,":[78],"we":[79,119,156],"present":[80],"various":[81],"state-of-the-art":[82],"GPU":[83,147,161,194],"optimization":[84],"strategies":[85],"DWT":[87,148,162,195],"implementation,":[88],"leveraging":[91],"shared":[92],"memory,":[93],"registers,":[94],"warp":[95],"shuffling":[96],"instructions,":[97],"thread-":[99],"instruction-level":[101],"parallelism":[102,169],"(TLP,":[103],"ILP),":[104],"finally":[106],"elaborate":[107],"our":[108,185],"hybrid":[109,168],"approach":[110],"further":[112],"boost":[113],"up":[114],"performance.":[116],"addition,":[118],"introduce":[120],"a":[121,137,143,177],"novel":[122],"mixed-band":[123,178],"memory":[124],"layout":[125],"Haar":[127],"DWT,":[128],"where":[129],"multi-level":[130],"can":[132,164],"be":[133,165],"carried":[134],"out":[135],"single":[138],"fused":[139],"kernel":[140],"launch.":[141],"As":[142],"result,":[144],"unlike":[145],"recent":[146],"methods":[149],"that":[150,158],"focus":[151],"mainly":[152],"on":[153],"maximizing":[154],"ILP,":[155],"show":[157],"optimal":[160],"performance":[163,183],"achieved":[166],"by":[167,188],"combining":[170],"both":[171],"TLP":[172],"ILP":[174],"together":[175],"approach.":[179],"We":[180],"demonstrate":[181],"proposed":[186],"method":[187],"comparison":[189],"with":[190],"other":[191],"CPU":[192],"methods.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}