{"id":"https://openalex.org/W1971418186","doi":"https://doi.org/10.1177/1094342015576848","title":"Scaling soft matter physics to thousands of graphics processing units in parallel","display_name":"Scaling soft matter physics to thousands of graphics processing units in parallel","publication_year":2015,"publication_date":"2015-03-25","ids":{"openalex":"https://openalex.org/W1971418186","doi":"https://doi.org/10.1177/1094342015576848","mag":"1971418186"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015576848","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015576848","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/b767ffb2-fac3-429c-875c-df0b902c72d8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109854669","display_name":"Alan Gray","orcid":"https://orcid.org/0009-0009-7731-1855"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alan Gray","raw_affiliation_strings":["EPCC, The University of Edinburgh, UK","EPCC, The University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103584438","display_name":"Alistair Hart","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123032","display_name":"Exascale (United Kingdom)","ror":"https://ror.org/032khhz22","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210123032"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alistair Hart","raw_affiliation_strings":["Cray Exascale Research Initiative Europe, UK","Cray Exascale Research Initiative Europe, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cray Exascale Research Initiative Europe, UK","institution_ids":["https://openalex.org/I4210123032"]},{"raw_affiliation_string":"Cray Exascale Research Initiative Europe, UK#TAB#","institution_ids":["https://openalex.org/I4210123032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038257980","display_name":"Oliver Henrich","orcid":"https://orcid.org/0000-0003-0384-982X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Henrich","raw_affiliation_strings":["EPCC, The University of Edinburgh, UK","EPCC, The University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025579578","display_name":"Kevin Stratford","orcid":"https://orcid.org/0000-0003-3491-2190"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Stratford","raw_affiliation_strings":["EPCC, The University of Edinburgh, UK","EPCC, The University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"EPCC, The University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6749,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8215832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"29","issue":"3","first_page":"274","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998999834060669,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.96670001745224,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8420935273170471},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7031494975090027},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.6564685702323914},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6279523372650146},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5820050239562988},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5188830494880676},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5178168416023254},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4991750717163086},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4987654685974121},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44531115889549255},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.43000757694244385},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21050959825515747},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1472097933292389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420935273170471},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7031494975090027},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.6564685702323914},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6279523372650146},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5820050239562988},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5188830494880676},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5178168416023254},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4991750717163086},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4987654685974121},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44531115889549255},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.43000757694244385},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21050959825515747},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1472097933292389},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342015576848","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015576848","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b767ffb2-fac3-429c-875c-df0b902c72d8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b767ffb2-fac3-429c-875c-df0b902c72d8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gray, A, Hart, A, Henrich, O & Stratford, K 2015, 'Scaling soft matter physics to thousands of graphics processing units in parallel', International Journal of High Performance Computing Applications, vol. 29, no. 3, pp. 274-283. https://doi.org/10.1177/1094342015576848","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:strathprints.strath.ac.uk:61626","is_oa":false,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/1039148.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b767ffb2-fac3-429c-875c-df0b902c72d8","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/b767ffb2-fac3-429c-875c-df0b902c72d8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/b767ffb2-fac3-429c-875c-df0b902c72d8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b767ffb2-fac3-429c-875c-df0b902c72d8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gray, A, Hart, A, Henrich, O & Stratford, K 2015, 'Scaling soft matter physics to thousands of graphics processing units in parallel', International Journal of High Performance Computing Applications, vol. 29, no. 3, pp. 274-283. https://doi.org/10.1177/1094342015576848","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4964432009","display_name":null,"funder_award_id":"EP/J007404/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1599770531","https://openalex.org/W1965754793","https://openalex.org/W2005786611","https://openalex.org/W2025706782","https://openalex.org/W2025798515","https://openalex.org/W2038714505","https://openalex.org/W2064744742","https://openalex.org/W2071296827","https://openalex.org/W2076028817","https://openalex.org/W2081457157","https://openalex.org/W2087722380","https://openalex.org/W2092687851","https://openalex.org/W2118929954","https://openalex.org/W2119950184","https://openalex.org/W2120900954","https://openalex.org/W2132348817","https://openalex.org/W2136559004","https://openalex.org/W2141579716","https://openalex.org/W2143061491","https://openalex.org/W2149788502","https://openalex.org/W2156861267","https://openalex.org/W2157670339","https://openalex.org/W2164417656","https://openalex.org/W2170400704","https://openalex.org/W3098588557","https://openalex.org/W3101833621","https://openalex.org/W3102078048","https://openalex.org/W3102708570","https://openalex.org/W3104790781","https://openalex.org/W4251386884"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2056717482","https://openalex.org/W2153506571","https://openalex.org/W3104348697","https://openalex.org/W1972148443","https://openalex.org/W2030707850","https://openalex.org/W2393490604","https://openalex.org/W2375309128","https://openalex.org/W4211066045"],"abstract_inverted_index":{"We":[0,34,54,72,104,124],"describe":[1,35,73],"a":[2,16,51,83,87],"multi-graphics":[3],"processing":[4,43],"unit":[5,44],"(GPU)":[6],"implementation":[7],"of":[8,18,90,148,177],"the":[9,40,62,68,79,91,111,129,141,146,163],"Ludwig":[10],"application,":[11],"which":[12,113],"specialises":[13],"in":[14,38,50,81,139],"simulating":[15],"variety":[17],"complex":[19,31],"fluids":[20],"via":[21],"lattice":[22],"Boltzmann":[23],"fluid":[24,32,80],"dynamics":[25],"coupled":[26],"to":[27,85,116,121,134],"additional":[28],"physics":[29],"describing":[30],"constituents.":[33],"our":[36,106],"methodology":[37],"augmenting":[39],"original":[41],"central":[42],"(CPU)":[45],"version":[46,152,165],"with":[47],"GPU":[48,63,69,94,151],"functionality":[49],"maintainable":[52],"fashion.":[53],"present":[55,125],"several":[56],"optimisations":[57],"that":[58,128,162],"maximise":[59],"performance":[60],"on":[61],"architecture":[64],"through":[65],"tuning":[66],"for":[67,110],"memory":[70],"hierarchy.":[71],"how":[74],"we":[75],"implement":[76],"particles":[77],"within":[78],"such":[82],"way":[84],"avoid":[86],"major":[88],"diversion":[89],"CPU":[92,164],"and":[93,179],"codebases,":[95],"whilst":[96],"minimising":[97],"data":[98],"transfer":[99],"at":[100,135,145],"each":[101],"time":[102,147],"step.":[103],"detail":[105],"halo-exchange":[107],"communication":[108],"phase":[109],"code,":[112],"exploits":[114],"overlapping":[115],"allow":[117],"efficient":[118],"parallel":[119],"scaling":[120,133],"many":[122],"GPUs.":[123,180],"results":[126],"showing":[127],"application":[130],"demonstrates":[131],"excellent":[132],"least":[136],"8192":[137],"GPUs":[138],"parallel,":[140],"largest":[142],"system":[143],"tested":[144],"writing.":[149],"The":[150],"(on":[153,166],"NVIDIA":[154],"K20X":[155],"GPUs)":[156],"is":[157],"around":[158],"3.5\u20135":[159],"times":[160],"faster":[161],"fully":[167],"utilised":[168],"AMD":[169],"Opteron":[170],"6274":[171],"16-core":[172],"CPUs),":[173],"comparing":[174],"equal":[175],"numbers":[176],"CPUs":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}