{"id":"https://openalex.org/W7224876160","doi":"https://doi.org/10.1145/3860328","title":"Parallelizing Instruction Scheduling for the GPU on the GPU","display_name":"Parallelizing Instruction Scheduling for the GPU on the GPU","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224876160","doi":"https://doi.org/10.1145/3860328"},"language":"en","primary_location":{"id":"doi:10.1145/3860328","doi":"https://doi.org/10.1145/3860328","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860328","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860328?download=true","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,"listed_in":["ccf-a","cwts-core","dongbi-b","jufo-1","norway-2","poland-70","russia-white-list-3"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3860328?download=true","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","observed_orcids":["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":false,"raw_author_name":"Ghassan Shobaki","raw_affiliation_strings":["Computer Science, California State University Sacramento"],"raw_orcid":"https://orcid.org/0000-0001-8727-671X","affiliations":[{"raw_affiliation_string":"Computer Science, California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160180854","display_name":"Joshua Grindstaff","orcid":"https://orcid.org/0009-0000-8504-6208","observed_orcids":["https://orcid.org/0009-0000-8504-6208"]},"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":"Joshua Grindstaff","raw_affiliation_strings":["Computer Science, California State University Sacramento"],"raw_orcid":"https://orcid.org/0009-0000-8504-6208","affiliations":[{"raw_affiliation_string":"Computer Science, California State University Sacramento","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","observed_orcids":["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":"Pinar Muyan-Ozcelik","raw_affiliation_strings":["Computer Science, California State University Sacramento"],"raw_orcid":"https://orcid.org/0000-0002-6671-8483","affiliations":[{"raw_affiliation_string":"Computer Science, California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160200321","display_name":"Joshua Hutton","orcid":"https://orcid.org/0009-0003-6549-542X","observed_orcids":["https://orcid.org/0009-0003-6549-542X"]},"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":"Joshua Hutton","raw_affiliation_strings":["California State University Sacramento"],"raw_orcid":"https://orcid.org/0009-0003-6549-542X","affiliations":[{"raw_affiliation_string":"California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160183237","display_name":"Phoebe Linck","orcid":"https://orcid.org/0009-0006-2276-8186","observed_orcids":["https://orcid.org/0009-0006-2276-8186"]},"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":"Phoebe Linck","raw_affiliation_strings":["California State University Sacramento"],"raw_orcid":"https://orcid.org/0009-0006-2276-8186","affiliations":[{"raw_affiliation_string":"California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094027448","display_name":"Vladislav Malyshenko","orcid":"https://orcid.org/0009-0005-4525-7605","observed_orcids":["https://orcid.org/0009-0005-4525-7605"]},"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 Sacramento"],"raw_orcid":"https://orcid.org/0009-0005-4525-7605","affiliations":[{"raw_affiliation_string":"California State University Sacramento","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","observed_orcids":["https://orcid.org/0000-0001-7314-5516"]},"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":"Austin Kerbow","raw_affiliation_strings":["Computer Science, California State University Sacramento"],"raw_orcid":"https://orcid.org/0000-0001-7314-5516","affiliations":[{"raw_affiliation_string":"Computer Science, California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160161286","display_name":"Vahl Gordon","orcid":"https://orcid.org/0000-0002-2422-1874","observed_orcids":["https://orcid.org/0000-0002-2422-1874"]},"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 Gordon","raw_affiliation_strings":["Computer Science, California State University Sacramento"],"raw_orcid":"https://orcid.org/0000-0002-2422-1874","affiliations":[{"raw_affiliation_string":"Computer Science, California State University Sacramento","institution_ids":["https://openalex.org/I43522216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43522216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8761046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/instruction-scheduling","display_name":"instruction scheduling","score":0.9919999837875366},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.6869999766349792},{"id":"https://openalex.org/keywords/ant-colony-optimization","display_name":"ant colony optimization","score":0.9789999723434448},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.9200000166893005},{"id":"https://openalex.org/keywords/register-pressure","display_name":"register pressure","score":0.9660000205039978},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"instruction-level parallelism","score":1.0},{"id":"https://openalex.org/keywords/parallel-algorithms","display_name":"parallel algorithms","score":0.41100001335144043},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.925000011920929},{"id":"https://openalex.org/keywords/np-hard-problems","display_name":"NP-hard problems","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9240999817848206},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7824000120162964},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C73564150","wikidata":"https://www.wikidata.org/wiki/Q11417093","display_name":"Instruction scheduling","level":5,"score":0.5450000166893005},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C40128228","wikidata":"https://www.wikidata.org/wiki/Q460851","display_name":"Ant colony optimization algorithms","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3860328","doi":"https://doi.org/10.1145/3860328","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860328","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860328?download=true","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,"listed_in":["ccf-a","cwts-core","dongbi-b","jufo-1","norway-2","poland-70","russia-white-list-3"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3860328","doi":"https://doi.org/10.1145/3860328","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860328","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860328?download=true","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,"listed_in":["ccf-a","cwts-core","dongbi-b","jufo-1","norway-2","poland-70","russia-white-list-3"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2181105169","display_name":"SHF:Small:RUI: Optimizing Compiler Instruction Scheduling Using GPU-Accelerated Intelligent Search","funder_award_id":"1911235","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320332867","display_name":"California State University, Sacramento","ror":"https://ror.org/03e26wv14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224876160.pdf","grobid_xml":"https://content.openalex.org/works/W7224876160.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W639132055","https://openalex.org/W1481848125","https://openalex.org/W1966914320","https://openalex.org/W1972912085","https://openalex.org/W1983540755","https://openalex.org/W2008154320","https://openalex.org/W2017069727","https://openalex.org/W2018474648","https://openalex.org/W2019733524","https://openalex.org/W2063769328","https://openalex.org/W2071828883","https://openalex.org/W2086039932","https://openalex.org/W2089688797","https://openalex.org/W2097377813","https://openalex.org/W2107941094","https://openalex.org/W2119650324","https://openalex.org/W2121056548","https://openalex.org/W2146995753","https://openalex.org/W2609986762","https://openalex.org/W2773453313","https://openalex.org/W2795671832","https://openalex.org/W2888909284","https://openalex.org/W2907733791","https://openalex.org/W2916770803","https://openalex.org/W2942544329","https://openalex.org/W2966451086","https://openalex.org/W3000154880","https://openalex.org/W3002332120","https://openalex.org/W3047630232","https://openalex.org/W3088480499","https://openalex.org/W3120529295","https://openalex.org/W3174357167","https://openalex.org/W3189632290","https://openalex.org/W3212823353","https://openalex.org/W4210408109","https://openalex.org/W4299796063"],"related_works":["https://openalex.org/W4392265902","https://openalex.org/W3007718266","https://openalex.org/W4210408109","https://openalex.org/W4324296979","https://openalex.org/W7096510562","https://openalex.org/W4323349073","https://openalex.org/W2124859146","https://openalex.org/W2585460399","https://openalex.org/W2573991456","https://openalex.org/W1971704039"],"abstract_inverted_index":{"In":[0,122],"this":[1,58,123,206,238],"article,":[2,124],"we":[3,125,196],"describe":[4,190],"how":[5],"to":[6,10,82,86,102,150,198,226,240,264,267,284],"use":[7],"the":[8,18,29,38,43,100,115,133,176,211,222,235,242,247,255,259,272,280,291],"GPU":[9,24,30,134,163,223],"parallelize":[11,200,285],"a":[12,23,32,61,74,130,184,191,286],"precise":[13,62,84],"search-based":[14],"algorithm":[15,63,203,289],"for":[16,22,28,142,166,204],"solving":[17,205],"instruction":[19],"scheduling":[20,27,220,233,253],"problem":[21,35,59,209],"target.":[25],"Instruction":[26],"is":[31,65,73,180,279],"multi-objective":[33,207],"optimization":[34,106,208,288],"in":[36,41,89,99,119],"which":[37,72],"challenge":[39],"lies":[40],"balancing":[42,156],"conflicting":[44],"objectives":[45],"of":[46,155,162,193,246,258,274],"minimizing":[47],"register":[48],"pressure":[49],"(RP)":[50],"and":[51,158,171,174,237],"maximizing":[52],"instruction-level":[53],"parallelism":[54],"(ILP).":[55],"We":[56,188],"solve":[57,103],"using":[60],"that":[64,78,127,168,195,217],"based":[66,182],"on":[67,132,183,210,221,234,290],"Ant":[68],"Colony":[69],"Optimization":[70],"(ACO),":[71],"nature-inspired":[75],"intelligent-search":[76,94],"technique":[77,131],"has":[79],"been":[80],"used":[81,98,118],"compute":[83],"solutions":[85,167],"NP-hard":[87,104],"problems":[88],"operations":[90],"research":[91],"(OR).":[92],"Such":[93],"techniques":[95,117,194],"were":[96],"not":[97,136],"past":[101],"compiler":[105,287],"problems,":[107],"because":[108],"they":[109],"require":[110],"substantially":[111],"more":[112],"computation":[113],"than":[114,230],"heuristic":[116],"production":[120,269],"compilers.":[121],"show":[126],"parallelizing":[128],"such":[129],"does":[135],"only":[137],"make":[138],"it":[139,145,148],"reasonably":[140],"practical":[141],"compilation,":[143],"but":[144],"also":[146,189],"makes":[147],"possible":[149],"simultaneously":[151],"explore":[152],"different":[153],"ways":[154],"RP":[157,170],"ILP.":[159],"Different":[160],"groups":[161],"threads":[164],"search":[165],"balance":[169],"ILP":[172],"differently,":[173],"then":[175],"most":[177],"balanced":[178],"solution":[179],"selected":[181],"certain":[185],"cost":[186],"function.":[187],"number":[192],"developed":[197],"efficiently":[199],"an":[201],"ACO":[202],"GPU.":[212,292],"The":[213],"experimental":[214],"evaluation":[215],"shows":[216],"parallel":[218],"ACO-based":[219,232,252],"runs":[224],"up":[225,263],"21":[227],"times":[228],"faster":[229],"sequential":[231],"CPU,":[236],"leads":[239],"reducing":[241],"total":[243],"compile":[244],"time":[245],"rocPRIM":[248],"benchmarks":[249,261],"by":[250,262],"42%.":[251],"improves":[254],"execution":[256],"speed":[257],"compiled":[260],"72%":[265],"relative":[266],"AMD\u2019s":[268],"scheduler.":[270],"To":[271],"best":[273],"our":[275,277],"knowledge,":[276],"work":[278],"first":[281],"successful":[282],"attempt":[283]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-31T00:00:00"}
