{"id":"https://openalex.org/W2886814729","doi":"https://doi.org/10.1145/3229710.3229711","title":"Experiences Using CPUs and GPUs for Cooperative Computation in a Multi-Physics Simulation","display_name":"Experiences Using CPUs and GPUs for Cooperative Computation in a Multi-Physics Simulation","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2886814729","doi":"https://doi.org/10.1145/3229710.3229711","mag":"2886814729"},"language":"en","primary_location":{"id":"doi:10.1145/3229710.3229711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1466935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012779678","display_name":"Olga Pearce","orcid":"https://orcid.org/0000-0002-1904-9627"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olga Pearce","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, California","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012779678"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.8722213506698608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7994445562362671},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7390173673629761},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6856358647346497},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6851505041122437},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.639430046081543},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6162671446800232},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.573884129524231},{"id":"https://openalex.org/keywords/multiphysics","display_name":"Multiphysics","score":0.5178916454315186},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5051389336585999},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.469009131193161},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4596445560455322},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45573458075523376},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.438810795545578},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2725266218185425},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.18284520506858826},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11622953414916992}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8722213506698608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994445562362671},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7390173673629761},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6856358647346497},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6851505041122437},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.639430046081543},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6162671446800232},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.573884129524231},{"id":"https://openalex.org/C46435376","wikidata":"https://www.wikidata.org/wiki/Q1829750","display_name":"Multiphysics","level":3,"score":0.5178916454315186},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5051389336585999},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.469009131193161},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4596445560455322},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45573458075523376},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.438810795545578},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2725266218185425},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.18284520506858826},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11622953414916992},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3229710.3229711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1466935","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1466935","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1466935","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1466935","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1993338334","https://openalex.org/W2041253549","https://openalex.org/W2063861626","https://openalex.org/W2078325682","https://openalex.org/W2078794610","https://openalex.org/W2106966138","https://openalex.org/W2132719357","https://openalex.org/W2139116943","https://openalex.org/W2171473263","https://openalex.org/W3187688612","https://openalex.org/W4234946335"],"related_works":["https://openalex.org/W2084426624","https://openalex.org/W3026055904","https://openalex.org/W2356602486","https://openalex.org/W2792869497","https://openalex.org/W4312133600","https://openalex.org/W2351992668","https://openalex.org/W2567205727","https://openalex.org/W2324828474","https://openalex.org/W2956082141","https://openalex.org/W1993991287"],"abstract_inverted_index":{"Top":[0],"supercomputers":[1],"in":[2,40,110,151,222],"the":[3,54,62,65,72,75,83,95,98,102,129,135,138,158,161,172,177,180,190,214,217,226],"TOP500":[4],"list":[5],"have":[6,37],"transitioned":[7],"from":[8],"homogeneous":[9],"node":[10,181],"architectures":[11,22,57],"toward":[12],"heterogeneous":[13,56,88,191,218],"manycore":[14],"nodes":[15,219],"with":[16,101],"accelerators":[17],"and":[18,137,167,174],"CPUs.":[19],"These":[20],"new":[21,55],"present":[23,106,195],"significant":[24],"challenges":[25],"to":[26,81,127,144,188,207,224],"developers":[27],"of":[28,47,71,74,94,148,171,176,212],"large-scale":[29],"multiphysics":[30,113],"applications,":[31],"especially":[32],"at":[33,116,203],"DOE":[34],"laboratories":[35],"that":[36],"invested":[38],"heavily":[39],"scalable":[41],"MPI":[42],"codes":[43],"over":[44],"decades.":[45],"Much":[46],"these":[48],"scientific":[49],"application":[50],"porting":[51],"efforts":[52],"for":[53,133,182,220],"are":[58],"focused":[59],"on":[60,64,86,97,179,198,216],"running":[61,91],"computation":[63,96],"accelerators,":[66],"which":[67,124],"usually":[68],"comprise":[69],">90%":[70],"FLOPS":[73,85],"system.":[76,154],"We":[77,105,140,194],"describe":[78],"an":[79,142,208],"approach":[80,143],"utilizing":[82],"remaining":[84],"a":[87,92,107,112,120,152],"machine":[89],"by":[90],"portion":[93],"CPUs":[99,215],"cooperatively":[100,150],"GPU":[103],"computation.":[104,183],"proof-of-concept":[108],"implementation":[109,156],"ARES,":[111],"ALE-AMR":[114],"code":[115,132],"LLNL.":[117],"ARES":[118],"uses":[119],"portability":[121],"layer,":[122],"RAJA,":[123],"enables":[125],"us":[126],"utilize":[128,145],"same":[130],"source":[131],"both":[134,146],"CPU":[136,173],"GPU.":[139],"develop":[141],"types":[147],"processors":[149],"mixed-processor":[153],"Our":[155],"divides":[157],"work":[159],"between":[160],"computing":[162,221],"resources":[163,192],"via":[164],"domain":[165],"decomposition,":[166],"utilizes":[168],"all":[169,175],"cores":[170],"GPUs":[178],"Load":[184],"balancing":[185],"is":[186],"necessary":[187],"use":[189],"effectively.":[193],"preliminary":[196],"results":[197],"early":[199],"delivery":[200],"pre-Sierra":[201],"machines":[202],"LLNL,":[204],"showing":[205],"up":[206],"18%":[209],"performance":[210],"benefit":[211],"using":[213,225],"addition":[223],"GPUs.":[227]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}