{"id":"https://openalex.org/W2034556713","doi":"https://doi.org/10.1109/mmsp.2012.6343431","title":"TCU: Thread compaction unit for GPGPU applications on mobile graphics hardware","display_name":"TCU: Thread compaction unit for GPGPU applications on mobile graphics hardware","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2034556713","doi":"https://doi.org/10.1109/mmsp.2012.6343431","mag":"2034556713"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2012.6343431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2012.6343431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)","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/A5037672133","display_name":"Yu\u2010Jung Chen","orcid":"https://orcid.org/0000-0003-4497-3747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jung Chen","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102744834","display_name":"Paishun Ting","orcid":"https://orcid.org/0000-0002-5675-3816"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pai-Shun Ting","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113708144","display_name":"Meng-Lin Yu","orcid":"https://orcid.org/0000-0003-2659-3783"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Meng-Lin Yu","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709988","display_name":"Chia-Ming Chang","orcid":"https://orcid.org/0000-0003-0390-6361"},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ming Chang","raw_affiliation_strings":["Institute for Information Industry, Smart Network &amp; System Institute 7F, No. 133, Sec. 4, Minsheng E. Rd., Taipei 105, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Industry, Smart Network &amp; System Institute 7F, No. 133, Sec. 4, Minsheng E. Rd., Taipei 105, Taiwan, R.O.C","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009305504","display_name":"Shao\u2010Yi Chien","orcid":"https://orcid.org/0000-0002-0634-6294"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Yi Chien","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Rd., Taipei 106, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"146","last_page":"151"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9968000054359436,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8493757843971252},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6697321534156799},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.525086522102356},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5228508114814758},{"id":"https://openalex.org/keywords/yarn","display_name":"Yarn","score":0.49558866024017334},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.49210160970687866},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.45255979895591736},{"id":"https://openalex.org/keywords/arithmetic-logic-unit","display_name":"Arithmetic logic unit","score":0.412400484085083},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.385850727558136},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36332476139068604},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24112030863761902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493757843971252},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6697321534156799},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.525086522102356},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5228508114814758},{"id":"https://openalex.org/C2778787235","wikidata":"https://www.wikidata.org/wiki/Q49007","display_name":"Yarn","level":2,"score":0.49558866024017334},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.49210160970687866},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.45255979895591736},{"id":"https://openalex.org/C100276221","wikidata":"https://www.wikidata.org/wiki/Q192903","display_name":"Arithmetic logic unit","level":2,"score":0.412400484085083},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.385850727558136},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36332476139068604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24112030863761902},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2012.6343431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2012.6343431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338484","display_name":"DOD Counterdrug Technology Development Program Office","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2007614029","https://openalex.org/W2033419168","https://openalex.org/W2096423380","https://openalex.org/W2105827278","https://openalex.org/W2128272608","https://openalex.org/W2140311411","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2169880332","https://openalex.org/W3097096317"],"related_works":["https://openalex.org/W2078851640","https://openalex.org/W2381070915","https://openalex.org/W2352481835","https://openalex.org/W2392493391","https://openalex.org/W4200164335","https://openalex.org/W2109471562","https://openalex.org/W2378508949","https://openalex.org/W3199747891","https://openalex.org/W2377434885","https://openalex.org/W2151195685"],"abstract_inverted_index":{"Thread":[0],"divergence":[1],"frequently":[2],"occurs":[3],"in":[4,123,137,143],"various":[5],"GPGPU":[6],"applications":[7],"while":[8],"parallel":[9,32],"threads":[10,61],"encounter":[11],"branching,":[12],"especially":[13],"for":[14,107],"multimedia":[15],"algorithms":[16],"involving":[17],"high-level":[18],"image":[19],"processing":[20,33],"and":[21,87,104,115,120],"computer":[22],"vision":[23],"algorithms.":[24],"Either":[25],"predicate":[26,78,114],"or":[27,80],"branch":[28,116],"instruction":[29],"degrades":[30],"the":[31],"performance":[34,106],"as":[35,132],"a":[36,46,64,68],"result":[37],"of":[38],"synchronization":[39],"cost.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"propose":[45],"configurable":[47],"thread":[48],"compaction":[49],"unit":[50],"(TCU)":[51],"to":[52,84,102,113],"relieve":[53],"such":[54],"execution":[55],"overhead.":[56],"Through":[57],"early-stage":[58],"compacting":[59,65,69],"divergent":[60],"by":[62,77],"evaluating":[63],"function":[66],"with":[67,96],"map,":[70],"TCU":[71,138],"can":[72,99,129],"prevent":[73],"redundant":[74],"executions":[75],"caused":[76],"instruction,":[79],"repetitively":[81],"invoking":[82],"processors":[83],"fetch":[85],"instructions":[86],"validate":[88],"effective":[89],"branches.":[90],"Our":[91],"simulation":[92],"results":[93],"show":[94],"that,":[95],"TCU,":[97],"GPUs":[98],"improve":[100],"up":[101],"24.5x":[103],"1.8x":[105],"Viola-Jones":[108],"face":[109],"detection":[110],"framework":[111],"compared":[112],"instruction.":[117],"Furthermore,":[118],"4.3x":[119],"1.4x":[121],"improvement":[122],"salient":[124],"region":[125],"linear":[126],"feature":[127],"extraction":[128],"be":[130],"achieved":[131],"well.":[133],"Finally,":[134],"cache":[135],"issue":[136],"architecture":[139],"is":[140],"also":[141],"discussed":[142],"detail.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
