{"id":"https://openalex.org/W2065493976","doi":"https://doi.org/10.1109/aspdac.2013.6509639","title":"Register and thread structure optimization for GPUs","display_name":"Register and thread structure optimization for GPUs","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2065493976","doi":"https://doi.org/10.1109/aspdac.2013.6509639","mag":"2065493976"},"language":"en","primary_location":{"id":"doi:10.1109/aspdac.2013.6509639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2013.6509639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 18th Asia and South Pacific Design Automation Conference (ASP-DAC)","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/A5100604862","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0003-0799-0054"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, China","Center for Energy-efficient Comput. & Applic., Peking Univ., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Energy-efficient Comput. & Applic., Peking Univ., Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079257435","display_name":"Zheng Cui","orcid":"https://orcid.org/0000-0002-3837-7407"},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zheng Cui","raw_affiliation_strings":["Advanced Digital Sciences Center, Singapore","Adv. Digital Sci. Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]},{"raw_affiliation_string":"Adv. Digital Sci. Center, Singapore, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090843153","display_name":"Kyle Rupnow","orcid":"https://orcid.org/0000-0003-2908-2225"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"K. Rupnow","raw_affiliation_strings":["Nanyang Technological University, Singapore","Adv. Digital Sci. Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Adv. Digital Sci. Center, Singapore, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA","Adv. Digital Sci. Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Adv. Digital Sci. Center, Singapore, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100604862"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2608,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80635658,"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":"461","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9003415107727051},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8570329546928406},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6937209963798523},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.68361896276474},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6588624119758606},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.6346408128738403},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5026655197143555},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4962485432624817},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.461823046207428},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44190797209739685},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4405042827129364},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4192923903465271},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41427552700042725},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22739964723587036},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22014179825782776},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17673185467720032},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.1670357584953308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9003415107727051},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8570329546928406},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6937209963798523},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.68361896276474},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6588624119758606},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.6346408128738403},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5026655197143555},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4962485432624817},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.461823046207428},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44190797209739685},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4405042827129364},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4192923903465271},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41427552700042725},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22739964723587036},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22014179825782776},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17673185467720032},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.1670357584953308}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspdac.2013.6509639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2013.6509639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 18th Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312066","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1595498733","https://openalex.org/W1979527452","https://openalex.org/W1992851788","https://openalex.org/W2012110315","https://openalex.org/W2080592089","https://openalex.org/W2106018915","https://openalex.org/W2110195531","https://openalex.org/W2113282196","https://openalex.org/W2130336316","https://openalex.org/W2167334577","https://openalex.org/W2295862081","https://openalex.org/W4250981202","https://openalex.org/W4251590233","https://openalex.org/W6653336569"],"related_works":["https://openalex.org/W4297672591","https://openalex.org/W2102568252","https://openalex.org/W1552591294","https://openalex.org/W1989457680","https://openalex.org/W1968980404","https://openalex.org/W2581122567","https://openalex.org/W2116123542","https://openalex.org/W2151195685","https://openalex.org/W2163046274","https://openalex.org/W2164949942"],"abstract_inverted_index":{"GPUs":[0],"are":[1],"an":[2],"increasingly":[3],"popular":[4],"implementation":[5],"platform":[6],"for":[7,117,130],"a":[8,43,52,67,76,133,153],"variety":[9,53],"of":[10,33,54,66,88,100,155,163],"general":[11],"purpose":[12],"applications":[13],"from":[14],"mobile":[15],"and":[16,25,45,64,103,137],"embedded":[17],"devices":[18],"to":[19,57,109,147,166],"high":[20],"performance":[21,41,65,82,127,161],"computing.":[22],"The":[23],"CUDA":[24],"OpenCL":[26],"parallel":[27],"programming":[28],"models":[29],"enable":[30],"easy":[31],"utilization":[32],"the":[34,61,86,114,145,149,175],"GPU's":[35],"resources.":[36],"However,":[37,70,113],"tuning":[38],"GPU":[39,156],"applications'":[40],"is":[42],"complex":[44],"labor":[46],"intensive":[47],"task.":[48],"Software":[49],"programmers":[50],"employ":[51],"optimization":[55,99,120],"techniques":[56,72,142],"explore":[58],"tradeoffs":[59],"between":[60],"thread":[62,81,104],"parallelism":[63],"single":[68,80],"thread.":[69],"prior":[71],"ignore":[73],"register":[74,101],"allocation,":[75],"significant":[77],"factor":[78],"in":[79],"and,":[83],"indirectly":[84],"affects":[85],"number":[87],"simultaneously":[89],"active":[90],"threads.":[91],"In":[92],"this":[93,118],"paper,":[94],"we":[95,125,158],"show":[96],"that":[97,143],"joint":[98,119],"allocation":[102],"structure":[105],"has":[106],"great":[107],"potential":[108],"significantly":[110],"improve":[111],"performance.":[112],"design":[115,139,169],"space":[116,140,170],"can":[121],"be":[122],"large;":[123],"therefore,":[124],"develop":[126],"metrics":[128,146],"appropriate":[129],"evaluation":[131],"within":[132],"compiler's":[134],"inner":[135],"loop":[136],"efficient":[138],"exploration":[141,171],"use":[144],"narrow":[148],"search":[150],"space.":[151],"Across":[152],"range":[154],"applications,":[157],"achieve":[159],"average":[160],"speedup":[162],"1.33X":[164],"(up":[165],"1.73X)":[167],"with":[168],"355X":[172],"faster":[173],"than":[174],"exhaustive":[176],"search.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}