{"id":"https://openalex.org/W4387769983","doi":"https://doi.org/10.1145/3626957","title":"Divergence Reduction in Monte Carlo Neutron Transport with On-GPU Asynchronous Scheduling","display_name":"Divergence Reduction in Monte Carlo Neutron Transport with On-GPU Asynchronous Scheduling","publication_year":2023,"publication_date":"2023-10-19","ids":{"openalex":"https://openalex.org/W4387769983","doi":"https://doi.org/10.1145/3626957"},"language":"en","primary_location":{"id":"doi:10.1145/3626957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626957","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Modeling and Computer Simulation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626957","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093091290","display_name":"Braxton Cuneo","orcid":"https://orcid.org/0000-0002-6493-0990"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Braxton Cuneo","raw_affiliation_strings":["Oregon State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-6493-0990","affiliations":[{"raw_affiliation_string":"Oregon State University, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101919598","display_name":"Mike Bailey","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Bailey","raw_affiliation_strings":["Oregon State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-2082-7262","affiliations":[{"raw_affiliation_string":"Oregon State University, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093091290"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":1.7625,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84572038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"1","first_page":"1","last_page":"25"},"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/T11949","display_name":"Nuclear Physics and Applications","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10597","display_name":"Nuclear reactor physics and engineering","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.8424334526062012},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7318171262741089},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7130362391471863},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.583381175994873},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5496582984924316},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5312371253967285},{"id":"https://openalex.org/keywords/neutron-transport","display_name":"Neutron transport","score":0.4866545796394348},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34254491329193115},{"id":"https://openalex.org/keywords/neutron","display_name":"Neutron","score":0.3318268656730652},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0985490083694458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424334526062012},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7318171262741089},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7130362391471863},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.583381175994873},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5496582984924316},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5312371253967285},{"id":"https://openalex.org/C66963500","wikidata":"https://www.wikidata.org/wiki/Q3338735","display_name":"Neutron transport","level":3,"score":0.4866545796394348},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34254491329193115},{"id":"https://openalex.org/C152568617","wikidata":"https://www.wikidata.org/wiki/Q2348","display_name":"Neutron","level":2,"score":0.3318268656730652},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0985490083694458},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626957","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Modeling and Computer Simulation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3626957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626957","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Modeling and Computer Simulation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2539028814","display_name":null,"funder_award_id":"DE-NA003967","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387769983.pdf","grobid_xml":"https://content.openalex.org/works/W4387769983.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W83190871","https://openalex.org/W1973538724","https://openalex.org/W1975625719","https://openalex.org/W1994316441","https://openalex.org/W1996485620","https://openalex.org/W2010459485","https://openalex.org/W2013247896","https://openalex.org/W2014496730","https://openalex.org/W2023859976","https://openalex.org/W2123914565","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2173641052","https://openalex.org/W2344044374","https://openalex.org/W2527612415","https://openalex.org/W2780665590","https://openalex.org/W2803393814","https://openalex.org/W2895519740","https://openalex.org/W2912470790","https://openalex.org/W2955615754","https://openalex.org/W3005741839","https://openalex.org/W3138993548","https://openalex.org/W3195420727","https://openalex.org/W4205474951","https://openalex.org/W4251292774","https://openalex.org/W4281630674"],"related_works":["https://openalex.org/W2748093601","https://openalex.org/W2116677773","https://openalex.org/W3132391082","https://openalex.org/W2924541683","https://openalex.org/W2155261584","https://openalex.org/W2186668756","https://openalex.org/W2584231425","https://openalex.org/W2150611273","https://openalex.org/W4207086172","https://openalex.org/W2042919702"],"abstract_inverted_index":{"While":[0],"Monte":[1],"Carlo":[2],"Neutron":[3],"Transport":[4],"(MCNT)":[5],"is":[6,21,26,93,148,230,236],"near-embarrasingly":[7],"parallel,":[8],"the":[9,27,76,94,115,164,226,233,243],"effectively":[10],"unpredictable":[11],"lifetime":[12],"of":[13,29,59,91,97,125,161,166,175,182,185,245],"neutrons":[14],"can":[15],"lead":[16],"to":[17,136,253],"divergence":[18],"when":[19],"MCNT":[20],"evaluated":[22],"on":[23,40],"GPUs.":[24],"Divergence":[25],"phenomenon":[28],"adjacent":[30],"threads":[31],"in":[32,75,139,242],"a":[33,55,123,149,158,171,212],"warp":[34,78],"executing":[35],"different":[36],"control":[37],"flow":[38],"paths;":[39],"GPUS,":[41],"it":[42,229,249],"reduces":[43],"performance":[44,168],"because":[45],"each":[46],"work":[47,135,147],"group":[48],"may":[49],"only":[50],"execute":[51],"one":[52],"path":[53],"at":[54],"time.":[56],"The":[57],"process":[58],"Thread":[60],"Data":[61],"Remapping":[62],"(TDR)":[63],"resolves":[64],"these":[65,199],"discrepancies":[66],"by":[67,108],"moving":[68],"data":[69,74,106,127],"across":[70,170],"hardware":[71],"such":[72],"that":[73,146,232,248],"same":[77],"will":[79],"be":[80,137],"processed":[81],"through":[82,128],"similar":[83],"paths.":[84],"A":[85],"common":[86],"issue":[87],"among":[88],"prior":[89,109],"implementations":[90],"TDR":[92],"synchronous":[95,221],"nature":[96],"its":[98],"remapping":[99,126],"and":[100,112,142,194,205,222,238,247],"processing":[101,110],"cycles,":[102],"which":[103,132],"exhaustively":[104,113],"sort":[105],"produced":[107],"passes":[111],"evaluate":[114],"sorted":[116],"data.":[117],"In":[118],"another":[119],"work,":[120],"we":[121,201],"defined":[122],"method":[124,235],"an":[129],"asynchronous":[130,223,234],"scheduler":[131],"allows":[133],"for":[134,152,219],"stored":[138],"shared":[140],"memory":[141,196,216,240],"deferred":[143],"arbitrarily":[144],"until":[145],"viable":[150],"option":[151],"low-divergence":[153],"evaluation.":[154],"This":[155],"article":[156],"surveys":[157],"wider":[159],"set":[160,174],"cases,":[162,200,246],"with":[163],"goal":[165],"characterizing":[167],"trends":[169],"more":[172,239],"comprehensive":[173],"parameters.":[176],"These":[177],"parameters":[178],"include":[179],"cross":[180],"sections":[181],"scattering/capturing/fission,":[183],"use":[184],"implicit":[186],"capture,":[187],"source":[188],"neutron":[189],"counts,":[190],"simulation":[191],"time":[192],"spans,":[193],"tuned":[195,214],"allocations.":[197],"Across":[198,225],"have":[202],"recorded":[203],"minimum":[204],"average":[206],"execution":[207],"times,":[208],"as":[209,211],"well":[210],"heuristically":[213],"near-optimal":[215],"allocation":[217],"size":[218],"both":[220],"scheduling.":[224],"collected":[227],"data,":[228],"shown":[231],"faster":[237],"efficient":[241],"majority":[244],"requires":[250],"less":[251],"tuning":[252],"achieve":[254],"competitive":[255],"performance.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
