{"id":"https://openalex.org/W4392265902","doi":"https://doi.org/10.1109/cgo57630.2024.10444869","title":"Instruction Scheduling for the GPU on the GPU","display_name":"Instruction Scheduling for the GPU on the GPU","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392265902","doi":"https://doi.org/10.1109/cgo57630.2024.10444869"},"language":"en","primary_location":{"id":"doi:10.1109/cgo57630.2024.10444869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5009270700","display_name":"Ghassan Shobaki","orcid":"https://orcid.org/0000-0001-8727-671X"},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ghassan Shobaki","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028111265","display_name":"P\u0131nar Muyan\u2010\u00d6z\u00e7elik","orcid":"https://orcid.org/0000-0002-6671-8483"},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P\u0131nar Muyan-\u00d6z\u00e7elik","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113129932","display_name":"Josh Hutton","orcid":null},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Hutton","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094027447","display_name":"Bruce Linck","orcid":null},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce Linck","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094027448","display_name":"Vladislav Malyshenko","orcid":null},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladislav Malyshenko","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055443277","display_name":"Austin Kerbow","orcid":"https://orcid.org/0000-0001-7314-5516"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Austin Kerbow","raw_affiliation_strings":["GPU-Compute Compiler Team, Advanced Micro Devices,United States","GPU-Compute Compiler Team, Advanced Micro Devices, United States"],"affiliations":[{"raw_affiliation_string":"GPU-Compute Compiler Team, Advanced Micro Devices,United States","institution_ids":["https://openalex.org/I4210137977","https://openalex.org/I1311921367"]},{"raw_affiliation_string":"GPU-Compute Compiler Team, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094027449","display_name":"Ronaldo Ramirez-Ortega","orcid":null},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronaldo Ramirez-Ortega","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109195137","display_name":"V. Scott Gordon","orcid":null},"institutions":[{"id":"https://openalex.org/I43522216","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14","country_code":"US","type":"education","lineage":["https://openalex.org/I43522216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahl Scott Gordon","raw_affiliation_strings":["California State University,Department of Computer Science,Sacramento,United States","Department of Computer Science, California State University, Sacramento, United States"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Computer Science,Sacramento,United States","institution_ids":["https://openalex.org/I43522216"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Sacramento, United States","institution_ids":["https://openalex.org/I43522216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5009270700"],"corresponding_institution_ids":["https://openalex.org/I43522216"],"apc_list":null,"apc_paid":null,"fwci":2.9365,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91445723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"435","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9950000047683716,"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":0.9024121761322021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8208855986595154},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7269319295883179},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6014383435249329},{"id":"https://openalex.org/keywords/ant-colony-optimization-algorithms","display_name":"Ant colony optimization algorithms","score":0.4480587840080261},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4355226159095764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21784085035324097},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.16129973530769348},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08066985011100769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9024121761322021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8208855986595154},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7269319295883179},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6014383435249329},{"id":"https://openalex.org/C40128228","wikidata":"https://www.wikidata.org/wiki/Q460851","display_name":"Ant colony optimization algorithms","level":2,"score":0.4480587840080261},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4355226159095764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21784085035324097},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.16129973530769348},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08066985011100769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo57630.2024.10444869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W42800076","https://openalex.org/W106298309","https://openalex.org/W1481848125","https://openalex.org/W1512940807","https://openalex.org/W1762731526","https://openalex.org/W1876846146","https://openalex.org/W1964323716","https://openalex.org/W1964625315","https://openalex.org/W1966914320","https://openalex.org/W1970851633","https://openalex.org/W1972912085","https://openalex.org/W1983540755","https://openalex.org/W1983815113","https://openalex.org/W2008154320","https://openalex.org/W2010793584","https://openalex.org/W2011495148","https://openalex.org/W2017069727","https://openalex.org/W2018474648","https://openalex.org/W2019733524","https://openalex.org/W2021066071","https://openalex.org/W2063769328","https://openalex.org/W2071828883","https://openalex.org/W2086039932","https://openalex.org/W2089688797","https://openalex.org/W2097377813","https://openalex.org/W2106972943","https://openalex.org/W2107941094","https://openalex.org/W2119650324","https://openalex.org/W2121056548","https://openalex.org/W2146995753","https://openalex.org/W2157103506","https://openalex.org/W2278840053","https://openalex.org/W2345839474","https://openalex.org/W2500609915","https://openalex.org/W2533998425","https://openalex.org/W2591732941","https://openalex.org/W2609986762","https://openalex.org/W2773453313","https://openalex.org/W2786544209","https://openalex.org/W2849597502","https://openalex.org/W2907733791","https://openalex.org/W2914775339","https://openalex.org/W2916770803","https://openalex.org/W2942544329","https://openalex.org/W2947061677","https://openalex.org/W2962770763","https://openalex.org/W2966451086","https://openalex.org/W2969047065","https://openalex.org/W3000154880","https://openalex.org/W3007718266","https://openalex.org/W3037637296","https://openalex.org/W3047630232","https://openalex.org/W3174357167","https://openalex.org/W3189632290","https://openalex.org/W4210408109","https://openalex.org/W4214551305","https://openalex.org/W4231586329","https://openalex.org/W4299796063","https://openalex.org/W6676080494","https://openalex.org/W6810055168"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973"],"abstract_inverted_index":{"In":[0,75],"this":[1,76,103,146,185],"paper,":[2],"we":[3,78,135],"show":[4,79],"how":[5],"to":[6,10,35,39,55,138,173,187,210,213,230],"use":[7],"the":[8,53,68,87,116,126,151,169,182,189,194,202,205,218,226,237],"GPU":[9,88,170],"parallelize":[11,140,231],"a":[12,27,83,106,130,158,232],"precise":[13,37],"instruction":[14,98],"scheduling":[15,99,167,180,200],"algorithm":[16,143,235],"that":[17,31,80,110,118,134,164],"is":[18,26,105,111,156,225],"based":[19],"on":[20,86,125,150,168,181,236],"Ant":[21],"Colony":[22],"Optimization":[23],"(ACO).":[24],"ACO":[25,124,142],"nature-inspired":[28],"intelligent-search":[29,47],"technique":[30,85],"has":[32],"been":[33],"used":[34,51,71],"compute":[36],"solutions":[38],"NP-hard":[40,57],"problems":[41,117],"in":[42,52,72,92,102],"operations":[43],"research":[44],"(OR).":[45],"Such":[46],"techniques":[48,70,133],"were":[49,119],"not":[50],"past":[54],"solve":[56],"compiler":[58,233],"optimization":[59,108,148,234],"problems,":[60],"because":[61],"they":[62],"require":[63],"substantially":[64],"more":[65,113],"computation":[66],"than":[67,115,177],"heuristic":[69],"production":[73,215],"compilers.":[74],"work,":[77],"parallelizing":[81],"such":[82],"compute-intensive":[84],"makes":[89],"using":[90,122],"it":[91],"compilation":[93],"reasonably":[94],"practical.":[95],"The":[96,153],"register-pressure-aware":[97],"problem":[100,109,149],"addressed":[101],"work":[104,224],"multi-objective":[107,147],"significantly":[112],"complex":[114],"previously":[120],"solved":[121],"parallel":[123,165],"GPU.":[127,152,159,238],"We":[128],"describe":[129],"number":[131],"of":[132,193,204,220],"have":[136],"developed":[137],"efficiently":[139],"an":[141],"for":[144],"solving":[145],"target":[154],"processor":[155],"also":[157],"Our":[160],"experimental":[161],"evaluation":[162],"shows":[163],"ACO-based":[166,179,199],"runs":[171],"up":[172,209],"27":[174],"times":[175],"faster":[176],"sequential":[178],"CPU,":[183],"and":[184],"leads":[186],"reducing":[188],"total":[190],"compile":[191],"time":[192],"rocPRIM":[195],"benchmarks":[196,207],"by":[197,208],"21%.":[198],"improves":[201],"execution-speed":[203],"compiled":[206],"74%":[211],"relative":[212],"AMD's":[214],"scheduler.":[216],"To":[217],"best":[219],"our":[221,223],"knowledge,":[222],"first":[227],"successful":[228],"attempt":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}