{"id":"https://openalex.org/W2766757481","doi":"https://doi.org/10.1109/hpec.2017.8091093","title":"Advanced load balancing for SPH simulations on multi-GPU architectures","display_name":"Advanced load balancing for SPH simulations on multi-GPU architectures","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2766757481","doi":"https://doi.org/10.1109/hpec.2017.8091093","mag":"2766757481"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2017.8091093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5012499296","display_name":"Kevin Verma","orcid":"https://orcid.org/0000-0002-8058-7520"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]},{"id":"https://openalex.org/I4210110916","display_name":"Engineering Software Steyr (Austria)","ror":"https://ror.org/0175s4d43","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210110916"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Kevin Verma","raw_affiliation_strings":["ESS Engineering Software Steyr GmbH, Austria","Institute for Integrated Circuits, Johannes Kepler University Linz, Austria"],"affiliations":[{"raw_affiliation_string":"ESS Engineering Software Steyr GmbH, Austria","institution_ids":["https://openalex.org/I4210110916"]},{"raw_affiliation_string":"Institute for Integrated Circuits, Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056958186","display_name":"Kamil Szewc","orcid":"https://orcid.org/0000-0002-9080-1551"},"institutions":[{"id":"https://openalex.org/I4210110916","display_name":"Engineering Software Steyr (Austria)","ror":"https://ror.org/0175s4d43","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210110916"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Kamil Szewc","raw_affiliation_strings":["ESS Engineering Software Steyr GmbH, Austria"],"affiliations":[{"raw_affiliation_string":"ESS Engineering Software Steyr GmbH, Austria","institution_ids":["https://openalex.org/I4210110916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004214923","display_name":"Robert Wille","orcid":"https://orcid.org/0000-0002-4993-7860"},"institutions":[{"id":"https://openalex.org/I4210110916","display_name":"Engineering Software Steyr (Austria)","ror":"https://ror.org/0175s4d43","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210110916"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Wille","raw_affiliation_strings":["ESS Engineering Software Steyr GmbH, Austria"],"affiliations":[{"raw_affiliation_string":"ESS Engineering Software Steyr GmbH, Austria","institution_ids":["https://openalex.org/I4210110916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012499296"],"corresponding_institution_ids":["https://openalex.org/I121883995","https://openalex.org/I4210110916"],"apc_list":null,"apc_paid":null,"fwci":3.1213,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91667982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9972000122070312,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8515380620956421},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7608264684677124},{"id":"https://openalex.org/keywords/smoothed-particle-hydrodynamics","display_name":"Smoothed-particle hydrodynamics","score":0.7413766384124756},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6287244558334351},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5882627964019775},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5716061592102051},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5619363784790039},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5597328543663025},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5203299522399902},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4614367187023163},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4500657320022583},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4453422725200653},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3803864121437073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14831200242042542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515380620956421},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7608264684677124},{"id":"https://openalex.org/C122564879","wikidata":"https://www.wikidata.org/wiki/Q733073","display_name":"Smoothed-particle hydrodynamics","level":2,"score":0.7413766384124756},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6287244558334351},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5882627964019775},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5716061592102051},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5619363784790039},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5597328543663025},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5203299522399902},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4614367187023163},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4500657320022583},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4453422725200653},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3803864121437073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14831200242042542},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2017.8091093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1503550591","https://openalex.org/W1766577897","https://openalex.org/W1815794495","https://openalex.org/W1980938760","https://openalex.org/W1994439127","https://openalex.org/W2026552799","https://openalex.org/W2027950887","https://openalex.org/W2044602433","https://openalex.org/W2057761913","https://openalex.org/W2072404169","https://openalex.org/W2114987640","https://openalex.org/W2115948634","https://openalex.org/W2127961966","https://openalex.org/W2131057369","https://openalex.org/W2139238466","https://openalex.org/W2168414272","https://openalex.org/W2409206186","https://openalex.org/W4295211600","https://openalex.org/W6630063115","https://openalex.org/W6638242195"],"related_works":["https://openalex.org/W2128417237","https://openalex.org/W2161462353","https://openalex.org/W1595151633","https://openalex.org/W2131630752","https://openalex.org/W2516240846","https://openalex.org/W94000989","https://openalex.org/W2064105003","https://openalex.org/W1537500193","https://openalex.org/W2535500072","https://openalex.org/W2116951845"],"abstract_inverted_index":{"Smoothed":[0],"Particle":[1],"Hydrodynamics":[2],"(SPH)":[3],"is":[4,16,99],"a":[5,19,52,110,124,129],"numerical":[6,54],"method":[7,41,127],"for":[8,85,128],"fluid":[9,15],"flow":[10],"modeling,":[11],"in":[12,36],"which":[13,29,146],"the":[14,37,89,116,148,154,159],"discretized":[17],"by":[18],"set":[20],"of":[21,68,106,158],"particles.":[22],"SPH":[23,83,107,132],"allows":[24],"to":[25,34,46,58,64,71,78,81,95,113],"model":[26],"complex":[27],"scenarios,":[28],"are":[30,144],"difficult":[31],"or":[32],"costly":[33],"measure":[35],"real":[38,60],"world.":[39],"This":[40],"has":[42],"several":[43,65],"advantages":[44],"compared":[45],"other":[47],"approaches,":[48],"but":[49],"suffers":[50],"from":[51],"huge":[53],"complexity.":[55],"In":[56,119],"order":[57],"simulate":[59],"life":[61],"phenomena,":[62],"up":[63],"hundred":[66],"millions":[67],"particles":[69],"have":[70],"be":[72,79],"considered.":[73],"Hence,":[74],"HPC":[75],"methods":[76],"need":[77],"leveraged":[80],"make":[82,108],"applicable":[84],"industrial":[86,131],"applications.":[87],"Distributing":[88],"respective":[90,117],"computations":[91],"among":[92],"different":[93],"GPUs":[94],"exploit":[96],"massive":[97],"parallelism":[98],"thereby":[100],"particularly":[101],"suited.":[102],"However,":[103],"certain":[104],"characteristics":[105],"it":[109],"non-trivial":[111],"task":[112],"properly":[114],"distribute":[115],"workload.":[118],"this":[120],"work,":[121],"we":[122],"present":[123],"load":[125],"balancing":[126],"CUDA-based":[130],"implementation":[133],"on":[134],"multi-GPU":[135],"architectures.":[136],"To":[137],"that":[138],"end,":[139],"dedicated":[140],"memory":[141],"handling":[142],"schemes":[143],"introduced,":[145],"reduce":[147],"synchronization":[149],"overhead.":[150],"Experimental":[151],"evaluations":[152],"confirm":[153],"scalability":[155],"and":[156],"efficiency":[157],"proposed":[160],"methods.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
