{"id":"https://openalex.org/W1985691044","doi":"https://doi.org/10.1109/cluster.2013.6702656","title":"Accelerating subsurface transport simulation on heterogeneous clusters","display_name":"Accelerating subsurface transport simulation on heterogeneous clusters","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W1985691044","doi":"https://doi.org/10.1109/cluster.2013.6702656","mag":"1985691044"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2013.6702656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3430380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111373927","display_name":"Oreste Villa","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Oreste Villa","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA","[Nvidia, Santa Clara, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[Nvidia, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075234132","display_name":"Nitin Gawande","orcid":"https://orcid.org/0000-0002-5761-1027"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin Gawande","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratories Richland WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041853964","display_name":"Antonino Tumeo","orcid":"https://orcid.org/0000-0001-9452-120X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonino Tumeo","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratories Richland WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3916,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86837856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"44","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10894","display_name":"Groundwater flow and contamination studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10894","display_name":"Groundwater flow and contamination studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11302","display_name":"CO2 Sequestration and Geologic Interactions","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10716","display_name":"Soil and Unsaturated Flow","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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":0.7683712244033813},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.7289994955062866},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7255124449729919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6314897537231445},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5740125775337219},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.5480140447616577},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4985034465789795},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.46760809421539307},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.4216794967651367},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.37060219049453735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3590812087059021},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33782172203063965},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.26752495765686035},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.2069026529788971},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12831175327301025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683712244033813},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.7289994955062866},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7255124449729919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6314897537231445},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5740125775337219},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.5480140447616577},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4985034465789795},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.46760809421539307},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.4216794967651367},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.37060219049453735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3590812087059021},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33782172203063965},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26752495765686035},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2069026529788971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12831175327301025},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cluster.2013.6702656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:3430380","is_oa":true,"landing_page_url":"https://zenodo.org/record/3430380","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3430380","is_oa":true,"landing_page_url":"https://zenodo.org/record/3430380","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W140614353","https://openalex.org/W1547888341","https://openalex.org/W1565899636","https://openalex.org/W1967834609","https://openalex.org/W1981534910","https://openalex.org/W2124451342","https://openalex.org/W2216909850"],"related_works":["https://openalex.org/W5176254","https://openalex.org/W1966287322","https://openalex.org/W2561626198","https://openalex.org/W4244491923","https://openalex.org/W4224251700","https://openalex.org/W2488393806","https://openalex.org/W2434613025","https://openalex.org/W2147274541","https://openalex.org/W1987016247","https://openalex.org/W2484220770"],"abstract_inverted_index":{"Reactive":[0],"transport":[1],"numerical":[2,98],"models":[3,15],"simulate":[4],"chemical":[5],"and":[6,53,62,73,124,126,162,207,235,291],"microbiological":[7],"reactions":[8,19],"that":[9,35,184,211,241],"occur":[10],"along":[11],"a":[12,21,50,54,79,254,284,292],"flow-path.":[13],"These":[14],"have":[16],"to":[17,219,247,271,280],"compute":[18],"for":[20,39,57,97,166,202],"large":[22,275],"number":[23],"of":[24,30,60,93,106,130,144,150,174,283],"locations.":[25],"They":[26],"solve":[27,248],"the":[28,37,43,66,91,107,142,148,171,175,195,226,244,250,263],"set":[29,59],"ordinary":[31],"differential":[32],"equations":[33],"(ODEs)":[34],"describes":[36],"reaction":[38],"each":[40,58],"location":[41],"through":[42],"Newton-Raphson":[44],"technique.":[45],"This":[46],"technique":[47],"involves":[48],"computing":[49,114],"Jacobian":[51],"matrix":[52],"residual":[55],"vector":[56],"equations,":[61],"then":[63],"solving":[64],"iteratively":[65],"linearized":[67],"system":[68],"by":[69],"performing":[70],"Gaussian":[71],"Elimination":[72],"LU":[74,100],"decomposition":[75],"until":[76],"convergence.":[77],"STOMP,":[78],"well":[80],"known":[81],"subsurface":[82,151],"flow":[83,152],"simulation":[84],"tool,":[85],"employs":[86],"matrices":[87,204],"with":[88,102,230,286],"sizes":[89],"in":[90,197],"order":[92],"100\u00d7100":[94],"elements":[95],"and,":[96],"accuracy,":[99],"factorization":[101],"full":[103,264],"pivoting":[104],"instead":[105],"faster":[108],"partial":[109],"pivoting.":[110],"Modern":[111],"high":[112],"performance":[113,188],"systems":[115,246],"are":[116],"heterogeneous":[117,190],"machines,":[118],"whose":[119],"nodes":[120,282],"integrate":[121],"both":[122,141],"CPUs":[123],"GPUs,":[125,206],"expose":[127],"unprecedented":[128],"amounts":[129],"parallelism.":[131],"To":[132],"exploit":[133],"all":[134],"their":[135],"computational":[136],"power,":[137],"applications":[138],"must":[139],"use":[140],"types":[143],"processing":[145],"elements.":[146],"For":[147],"case":[149],"simulation,":[153],"this":[154,178,217],"mainly":[155],"requires":[156],"implementing":[157,198],"efficient":[158,164],"batched":[159,199,227],"LU-based":[160,200],"solvers":[161,201],"identifying":[163],"solutions":[165],"enabling":[167],"load":[168,239],"balancing":[169],"among":[170],"different":[172],"processors":[173],"system.":[176],"In":[177],"paper":[179],"we":[180,224],"discuss":[181],"two":[182,251,287],"approaches":[183],"allow":[185],"scaling":[186],"STOMP's":[187,213],"on":[189,205,274,278],"clusters.":[191],"We":[192,215,256],"initially":[193],"identify":[194],"challenges":[196],"small":[203],"propose":[208],"an":[209,231,237],"implementation":[210,218],"fulfills":[212],"requirements.":[214],"compare":[216],"other":[220],"existing":[221],"solutions.":[222],"Then,":[223],"combine":[225],"GPU":[228],"solver":[229],"OpenMP-based":[232],"CPU":[233],"solver,":[234],"present":[236],"adaptive":[238],"balancer":[240],"dynamically":[242],"distributes":[243],"linear":[245],"between":[249],"components":[252],"inside":[253],"node.":[255,296],"show":[257],"how":[258],"these":[259],"approaches,":[260],"integrated":[261],"into":[262],"application,":[265],"provide":[266],"speed":[267],"ups":[268],"from":[269],"6":[270],"7":[272],"times":[273],"problems,":[276],"executed":[277],"up":[279],"16":[281],"cluster":[285],"AMD":[288],"Opteron":[289],"6272":[290],"Tesla":[293],"M2090":[294],"per":[295]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}