{"id":"https://openalex.org/W2765505246","doi":"https://doi.org/10.1145/3149412.3149416","title":"Performance and Power Characteristics and Optimizations of Hybrid MPI/OpenMP LULESH Miniapps under Various Workloads","display_name":"Performance and Power Characteristics and Optimizations of Hybrid MPI/OpenMP LULESH Miniapps under Various Workloads","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2765505246","doi":"https://doi.org/10.1145/3149412.3149416","mag":"2765505246"},"language":"en","primary_location":{"id":"doi:10.1145/3149412.3149416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149412.3149416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Energy Efficient Supercomputing","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/A5072646801","display_name":"Xingfu Wu","orcid":"https://orcid.org/0000-0001-8150-5171"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingfu Wu","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028916710","display_name":"Valerie Taylor","orcid":"https://orcid.org/0000-0001-6061-0191"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerie Taylor","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103871090","display_name":"Jeanine Cook","orcid":"https://orcid.org/0009-0007-2747-8046"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeanine Cook","raw_affiliation_strings":["Computer Science Res. Institute, Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Computer Science Res. Institute, Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019266023","display_name":"Tanner Juedeman","orcid":null},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanner Juedeman","raw_affiliation_strings":["Dept. of Computer Science, New Mexico State University"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072646801"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.2253,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51708537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8495336771011353},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7376977205276489},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6451655030250549},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.556690514087677},{"id":"https://openalex.org/keywords/bandwidth-throttling","display_name":"Bandwidth throttling","score":0.5557592511177063},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4938655495643616},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4839189648628235},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.44864967465400696},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.4184214174747467},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4162823557853699},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4020649194717407},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3868441879749298},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3818994164466858},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3451550602912903},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1198054850101471},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11144888401031494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8495336771011353},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7376977205276489},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6451655030250549},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.556690514087677},{"id":"https://openalex.org/C173061102","wikidata":"https://www.wikidata.org/wiki/Q478819","display_name":"Bandwidth throttling","level":3,"score":0.5557592511177063},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4938655495643616},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4839189648628235},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.44864967465400696},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.4184214174747467},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4162823557853699},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4020649194717407},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3868441879749298},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3818994164466858},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3451550602912903},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1198054850101471},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11144888401031494},{"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"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:10.1145/3149412.3149416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149412.3149416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Energy Efficient Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1942400916","https://openalex.org/W1983472241","https://openalex.org/W1993815837","https://openalex.org/W2014584442","https://openalex.org/W2016344549","https://openalex.org/W2025123206","https://openalex.org/W2031867463","https://openalex.org/W2032136713","https://openalex.org/W2070310479","https://openalex.org/W2130604611","https://openalex.org/W2138361296","https://openalex.org/W2149813938","https://openalex.org/W2151587416","https://openalex.org/W2185100167","https://openalex.org/W2268868827","https://openalex.org/W2466495821","https://openalex.org/W2536542975","https://openalex.org/W4244593655"],"related_works":["https://openalex.org/W2393348554","https://openalex.org/W2349133582","https://openalex.org/W1606512765","https://openalex.org/W2010203168","https://openalex.org/W2113326345","https://openalex.org/W3151308896","https://openalex.org/W183653846","https://openalex.org/W1520729804","https://openalex.org/W2015072665","https://openalex.org/W2069213387"],"abstract_inverted_index":{"Energy":[0],"efficient":[1],"execution":[2],"of":[3,18,32,63,77],"scientific":[4],"applications":[5],"requires":[6],"insight":[7,86],"into":[8],"how":[9],"HPC":[10],"system":[11],"features":[12],"affect":[13],"the":[14,19,85,102,107,120],"performance":[15,28,64,72],"and":[16,26,29,65,74,91],"power":[17,30],"applications.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"analyze":[25],"model":[27],"characteristics":[31],"hybrid":[33],"MPI/OpenMP":[34],"LULESH":[35],"(Livermore":[36],"Unstructured":[37],"Lagrange":[38],"Explicit":[39],"Shock":[40],"Hydrodynamics)":[41],"miniapps":[42],"under":[43,93],"various":[44,94],"workloads":[45],"using":[46],"MuMMI":[47],"(Multiple":[48],"Metrics":[49],"Modeling":[50],"Infrastructure).":[51],"Output":[52],"from":[53,88],"these":[54],"models":[55,90],"is":[56],"then":[57],"used":[58],"to":[59,79,101,112],"guide":[60],"code":[61],"optimizations":[62],"power.":[66],"Our":[67],"optimization":[68],"methods":[69],"result":[70],"in":[71,106],"improvement":[73],"energy":[75,108],"savings":[76,109],"up":[78],"approximately":[80],"10%.":[81],"Further,":[82],"based":[83],"on":[84,123,131],"learned":[87],"our":[89],"measurements":[92],"workloads,":[95],"applying":[96],"DCT":[97],"(Dynamic":[98],"Concurrency":[99],"Throttling)":[100],"optimized":[103],"codes":[104],"results":[105,122],"by":[110],"43.12%":[111],"58.30%":[113],"for":[114],"different":[115],"problem":[116],"sizes":[117],"compared":[118],"with":[119,126],"baseline":[121],"27":[124],"nodes":[125],"32":[127],"threads":[128],"per":[129],"node":[130],"a":[132],"36-node":[133],"Intel":[134],"Haswell":[135],"testbed":[136],"cluster":[137],"Shepard.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}