{"id":"https://openalex.org/W4401408745","doi":"https://doi.org/10.1145/3673038.3673090","title":"Multi-level Load Balancing Strategies for Massively Parallel Smoothed Particle Hydrodynamics Simulation","display_name":"Multi-level Load Balancing Strategies for Massively Parallel Smoothed Particle Hydrodynamics Simulation","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408745","doi":"https://doi.org/10.1145/3673038.3673090"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673090","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3673038.3673090","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042126801","display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0005-2125-4119"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0005-2125-4119","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084267553","display_name":"Ziyu Zhang","orcid":"https://orcid.org/0000-0001-6293-7227"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Zhang","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-6293-7227","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060336115","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0009-9644-8574"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0009-9644-8574","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436158","display_name":"Junshi Chen","orcid":"https://orcid.org/0000-0002-6487-3658"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junshi Chen","raw_affiliation_strings":["University of Science and Technology of China, China and Laoshan Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-6487-3658","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China and Laoshan Laboratory, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085758579","display_name":"Hong An","orcid":"https://orcid.org/0000-0002-3900-3722"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong An","raw_affiliation_strings":["University of Science and Technology of China, China and Laoshan Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-3900-3722","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China and Laoshan Laboratory, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014834859","display_name":"Zhanming Wang","orcid":"https://orcid.org/0009-0006-0300-2572"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanming Wang","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0006-0300-2572","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071277441","display_name":"Longkui Chen","orcid":"https://orcid.org/0000-0001-8652-1832"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longkui Chen","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-8652-1832","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5042126801"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13021686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11694","display_name":"Fluid Dynamics Simulations and Interactions","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11694","display_name":"Fluid Dynamics Simulations and Interactions","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11382","display_name":"Fluid Dynamics and Heat Transfer","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/smoothed-particle-hydrodynamics","display_name":"Smoothed-particle hydrodynamics","score":0.8557569980621338},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.7122349143028259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6998263001441956},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.540084958076477},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4632849097251892},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38841909170150757},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.2558406889438629},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16915550827980042},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1096850037574768}],"concepts":[{"id":"https://openalex.org/C122564879","wikidata":"https://www.wikidata.org/wiki/Q733073","display_name":"Smoothed-particle hydrodynamics","level":2,"score":0.8557569980621338},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.7122349143028259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998263001441956},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.540084958076477},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4632849097251892},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38841909170150757},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.2558406889438629},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16915550827980042},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1096850037574768},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673090","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673090","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1538076361","https://openalex.org/W1713170507","https://openalex.org/W1994439127","https://openalex.org/W2021058167","https://openalex.org/W2026730653","https://openalex.org/W2040935682","https://openalex.org/W2080977367","https://openalex.org/W2103660617","https://openalex.org/W2142636916","https://openalex.org/W2613097798","https://openalex.org/W2620844076","https://openalex.org/W2744007529","https://openalex.org/W2766757481","https://openalex.org/W2802951544","https://openalex.org/W2902659137","https://openalex.org/W3036569438","https://openalex.org/W3087070007","https://openalex.org/W3126566516","https://openalex.org/W3131779325","https://openalex.org/W4230128103","https://openalex.org/W4239711157","https://openalex.org/W4252935484","https://openalex.org/W4309825983","https://openalex.org/W4311805845"],"related_works":["https://openalex.org/W2023839151","https://openalex.org/W1774183074","https://openalex.org/W2057488824","https://openalex.org/W2334687145","https://openalex.org/W2178011914","https://openalex.org/W4235962491","https://openalex.org/W2061778832","https://openalex.org/W1513001507","https://openalex.org/W2257153718","https://openalex.org/W3134702077"],"abstract_inverted_index":{"In":[0],"the":[1,24,47,53,133,143,147,156,160,164],"field":[2],"of":[3,28,44,55,135,166,215],"computational":[4,167,182],"fluid":[5,19,30],"dynamics,":[6],"Smoothed":[7],"Particle":[8],"Hydrodynamics":[9],"(SPH)":[10],"serves":[11],"as":[12,33,46],"a":[13,72,80,92,113,177,213],"powerful":[14],"tool":[15],"for":[16],"investigating":[17],"complex":[18],"interactions":[20],"and":[21,37,79,131,175,195],"instabilities.":[22],"For":[23],"practical":[25],"SPH":[26,61,74],"simulation":[27],"large-scale":[29,60],"phenomena":[31],"such":[32],"tsunamis,":[34],"volcanic":[35],"eruptions,":[36],"planetary":[38],"collisions,":[39],"it":[40],"typically":[41],"requires":[42],"billions":[43],"particles,":[45],"numerical":[48],"resolution":[49],"increases":[50,163],"proportionally":[51],"with":[52,66,208,212],"number":[54],"particles.":[56],"To":[57],"efficiently":[58],"conduct":[59],"simulations":[62],"on":[63,98,138,146,159],"modern":[64],"supercomputers":[65],"massive":[67],"many-core":[68],"processors,":[69],"we":[70],"propose":[71],"novel":[73],"implementation":[75,186],"leveraging":[76],"multi-level":[77],"parallelism":[78],"corresponding":[81],"three-level":[82],"load":[83,87,136,152],"balancing":[84,88,137,153],"strategy.":[85,119],"Our":[86,120],"approach":[89],"comprises:":[90],"(1)":[91],"process-level":[93],"domain":[94],"decomposition":[95],"algorithm":[96],"based":[97],"an":[99,106],"improved":[100],"1D":[101],"partitioning":[102],"exact":[103],"algorithm;":[104],"(2)":[105],"adaptive":[107],"recursive":[108],"cell":[109],"subdivision":[110],"method;":[111],"(3)":[112],"fine-grained":[114],"dynamic":[115],"thread-level":[116],"task":[117],"scheduling":[118],"experiment":[121],"uses":[122],"1":[123,198,209],"billion":[124],"particles":[125,194],"to":[126,173,190,200],"simulate":[127],"converging":[128],"Richtmyer\u2013Meshkov":[129],"instability":[130],"verifies":[132],"effect":[134],"new":[139],"Sunway":[140],"supercomputer.":[141],"As":[142],"shockwave":[144],"converges":[145],"central":[148],"interface":[149],"area,":[150],"our":[151,185],"strategy":[154],"breaks":[155],"bottleneck":[157],"constraints":[158],"slowest":[161],"node,":[162],"balance":[165],"loads":[168],"between":[169],"nodes":[170],"from":[171,197],"30.01%":[172],"91.48%,":[174],"achieves":[176],"2.8":[178],"\u00d7":[179],"improvement":[180],"in":[181],"performance.":[183],"Finally,":[184],"enables":[187],"each":[188],"CPU":[189,199],"handle":[191],"10":[192],"million":[193,206],"scale":[196],"100,000":[201],"CPUs":[202],"(in":[203],"total":[204],"39":[205],"cores":[207],"trillion":[210],"particles)":[211],"performance":[214],"80.4%":[216],"parallel":[217],"efficiency.":[218]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
