{"id":"https://openalex.org/W2860285680","doi":"https://doi.org/10.1145/3219104.3229279","title":"Combining HPC and Big Data Infrastructures in Large-Scale Post-Processing of Simulation Data","display_name":"Combining HPC and Big Data Infrastructures in Large-Scale Post-Processing of Simulation Data","publication_year":2018,"publication_date":"2018-07-12","ids":{"openalex":"https://openalex.org/W2860285680","doi":"https://doi.org/10.1145/3219104.3229279","mag":"2860285680"},"language":"en","primary_location":{"id":"doi:10.1145/3219104.3229279","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229279","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229279","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience on Advanced Research Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229279","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100345948","display_name":"Yu Li","orcid":"https://orcid.org/0000-0003-4355-2764"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["School of Computing, Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330122","display_name":"Xiaohong Zhang","orcid":"https://orcid.org/0000-0003-2481-2663"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohong Zhang","raw_affiliation_strings":["Chemical and Biomolecular Engineering, Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical and Biomolecular Engineering, Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078753236","display_name":"Ashwin Trikuta Srinath","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Srinath","raw_affiliation_strings":["Clemson Computing & Information Technology, Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson Computing & Information Technology, Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085121177","display_name":"Rachel B. Getman","orcid":"https://orcid.org/0000-0003-0755-0534"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel B. Getman","raw_affiliation_strings":["Chemical and Biomolecular Engineering, Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical and Biomolecular Engineering, Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103239762","display_name":"Linh B. Ngo","orcid":"https://orcid.org/0000-0002-9889-2742"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linh B. Ngo","raw_affiliation_strings":["Clemson Computing & Information Technology, Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson Computing & Information Technology, Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8557769060134888},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8417325615882874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8283896446228027},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8016484975814819},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6238362193107605},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.564496636390686},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5401524305343628},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5295100212097168},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5085076093673706},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4843484163284302},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43849754333496094},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.42366504669189453},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42326292395591736},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3391345739364624},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21498996019363403},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.204685240983963}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8557769060134888},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8417325615882874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283896446228027},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8016484975814819},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6238362193107605},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.564496636390686},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5401524305343628},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5295100212097168},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5085076093673706},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4843484163284302},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43849754333496094},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.42366504669189453},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42326292395591736},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3391345739364624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21498996019363403},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.204685240983963},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219104.3229279","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229279","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229279","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience on Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3219104.3229279","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229279","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229279","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience on Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G3622229303","display_name":null,"funder_award_id":"CBET-1554385","funder_id":"https://openalex.org/F4320337390","funder_display_name":"Division of Chemical, Bioengineering, Environmental, and Transport Systems"},{"id":"https://openalex.org/G4161271238","display_name":null,"funder_award_id":"CBET-1554385","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4181809312","display_name":"CAREER:Hierarchical Modeling for Rational Catalyst Design in Aqueous Conditions","funder_award_id":"1554385","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5965542374","display_name":null,"funder_award_id":"CBET-1554385","funder_id":"https://openalex.org/F4320309106","funder_display_name":"Clemson University"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309106","display_name":"Clemson University","ror":"https://ror.org/037s24f05"},{"id":"https://openalex.org/F4320337390","display_name":"Division of Chemical, Bioengineering, Environmental, and Transport Systems","ror":"https://ror.org/0471zv972"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2860285680.pdf","grobid_xml":"https://content.openalex.org/works/W2860285680.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W80878036","https://openalex.org/W2014967136","https://openalex.org/W2019465613","https://openalex.org/W2147304506","https://openalex.org/W2147988069","https://openalex.org/W2189465200","https://openalex.org/W2190012392","https://openalex.org/W2337296361","https://openalex.org/W2403379684","https://openalex.org/W2523288541","https://openalex.org/W2590682660","https://openalex.org/W2913305800","https://openalex.org/W4250759912","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W3191926225","https://openalex.org/W2525033434","https://openalex.org/W4280533024","https://openalex.org/W4300992253","https://openalex.org/W4226266853","https://openalex.org/W1942762218","https://openalex.org/W4210252074","https://openalex.org/W1985270856","https://openalex.org/W3092201768","https://openalex.org/W2796632413"],"abstract_inverted_index":{"Advances":[0],"in":[1,25,35,91],"scientific":[2,124],"software":[3],"and":[4,14,28,90,115,151,167],"computing":[5,113,139,147],"infrastructure":[6,119],"have":[7,30],"enabled":[8],"researchers":[9,63],"across":[10,165],"disciplines":[11],"to":[12,32,56,69,102,120,161,174,208],"simulate":[13],"model":[15],"highly":[16],"complex":[17,168],"systems.":[18],"At":[19],"the":[20,36,75,108,134,178],"same":[21],"time,":[22],"these":[23,78,145,172],"increases":[24],"simulation":[26,159,190],"duration":[27],"scale":[29],"led":[31],"significant":[33,193],"growths":[34],"sizes":[37],"of":[38,48,77,110,136,203,213],"output":[39,79],"data,":[40,80],"which":[41],"can":[42,191],"be":[43,162,175,209],"as":[44,46],"much":[45],"hundreds":[47],"gigabytes":[49],"or":[50],"more.":[51],"While":[52],"there":[53],"exist":[54],"solutions":[55,205],"assist":[57],"with":[58],"most":[59,81,92],"standard":[60],"post-simulation":[61],"analytics,":[62],"must":[64],"develop":[65],"their":[66],"own":[67],"code":[68,201],"support":[70,121],"customized":[71],"analytical":[72,169],"tasks.":[73],"Given":[74],"nature":[76],"naive":[82],"in-house":[83],"sequential":[84],"codes":[85],"end":[86],"up":[87],"being":[88],"inefficient,":[89],"cases,":[93],"time-consuming.":[94],"In":[95],"this":[96,103],"paper,":[97],"we":[98,128],"propose":[99],"a":[100,111,116,130,137,184,197,214],"solution":[101],"issue":[104],"by":[105],"transparently":[106],"combining":[107],"strengths":[109],"high-performance":[112],"cluster":[114],"big":[117],"data":[118,160,173],"an":[122],"end-to-end":[123],"workflow.":[125,199],"More":[126],"specifically,":[127],"present":[129],"case":[131],"study":[132],"around":[133],"design":[135],"research":[138],"environment":[140,157],"at":[141],"Clemson":[142],"University":[143],"where":[144],"two":[146],"systems":[148,166],"are":[149],"integrated":[150],"accessible":[152],"from":[153],"one":[154],"another.":[155],"This":[156],"allows":[158],"automatically":[163],"transferred":[164],"tasks":[170],"on":[171],"developed":[176],"using":[177],"Hadoop/Spark":[179,204],"frameworks.":[180],"Results":[181],"show":[182],"that":[183,212],"hybrid":[185],"workflow":[186],"for":[187],"molecular":[188],"dynamics":[189],"provide":[192],"performance":[194],"improvements":[195],"over":[196],"traditional":[198,215],"Furthermore,":[200],"complexity":[202],"is":[206],"shown":[207],"less":[210],"than":[211],"solution.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}