{"id":"https://openalex.org/W2141801163","doi":"https://doi.org/10.1145/2751205.2751246","title":"A Nested Partitioning Algorithm for Adaptive Meshes on Heterogeneous Clusters","display_name":"A Nested Partitioning Algorithm for Adaptive Meshes on Heterogeneous Clusters","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2141801163","doi":"https://doi.org/10.1145/2751205.2751246","mag":"2141801163"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751246","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2751205.2751246?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2751205.2751246?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051806400","display_name":"Hari Sundar","orcid":"https://orcid.org/0000-0001-9001-5107"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hari Sundar","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA","University of Utah, Salt Lake City, UT, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA#TAB#","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049331711","display_name":"Omar Ghattas","orcid":"https://orcid.org/0000-0001-7742-2509"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Ghattas","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA","University of Texas at Austin, Austin, TX USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Austin, TX USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051806400"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.323,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.60205461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.8434984683990479},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7728502750396729},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.720786452293396},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6912627220153809},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6343801021575928},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.559775173664093},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5233384966850281},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4729287922382355},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41778916120529175},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32166969776153564},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.29388874769210815},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.20628345012664795},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0912313163280487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434984683990479},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7728502750396729},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.720786452293396},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6912627220153809},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6343801021575928},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.559775173664093},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5233384966850281},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4729287922382355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41778916120529175},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32166969776153564},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.29388874769210815},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.20628345012664795},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0912313163280487},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751246","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2751205.2751246?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2751205.2751246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751246","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2751205.2751246?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2796149713","display_name":null,"funder_award_id":"CMMI-1028889","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3618738895","display_name":null,"funder_award_id":"DE-SC0009286","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141801163.pdf","grobid_xml":"https://content.openalex.org/works/W2141801163.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W348433680","https://openalex.org/W1484226837","https://openalex.org/W1583515859","https://openalex.org/W1776498962","https://openalex.org/W1964031104","https://openalex.org/W1979313559","https://openalex.org/W2008373862","https://openalex.org/W2023944418","https://openalex.org/W2048007344","https://openalex.org/W2056984487","https://openalex.org/W2073061372","https://openalex.org/W2087479145","https://openalex.org/W2119343454","https://openalex.org/W2170215184","https://openalex.org/W4234044751","https://openalex.org/W4237196420","https://openalex.org/W4251197584"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W2883383827","https://openalex.org/W4214765606","https://openalex.org/W2058527440","https://openalex.org/W2334331871","https://openalex.org/W2612954225","https://openalex.org/W2952973539"],"abstract_inverted_index":{"In":[0],"the":[1,4,23,34,37,87,96,99,118,144,150,153,209,214],"era":[2],"of":[3,25,143,152,173,213],"accelerator,":[5,100],"load":[6,74],"balancing":[7],"strategies":[8],"that":[9,32,66],"are":[10],"well-understood":[11],"for":[12,44,57,184],"traditional":[13,119],"homogeneous":[14,46],"supercomputers":[15],"must":[16],"be":[17,92,108],"re-worked":[18],"in":[19,115,122,132],"order":[20,180,186],"to":[21,78,91,107,117,175,189,207],"address":[22],"problem":[24],"distributing":[26],"work":[27],"across":[28],"heterogeneous":[29],"hardware":[30],"such":[31],"neither":[33],"CPU":[35,97,130],"nor":[36],"accelerator":[38,124],"is":[39,114],"left":[40],"idle.":[41],"Whereas":[42],"partitioning":[43,56,64,155],"a":[45,62,139,158,178,190],"system":[47,60],"need":[48],"only":[49],"balance":[50],"node-level":[51],"workload":[52],"against":[53],"single-node":[54],"performance,":[55],"an":[58,69],"accelerator-enabled":[59,215],"requires":[61],"nested":[63],"scheme":[65,85,156],"ensures":[67],"both":[68,95,133],"optimal":[70],"intra-node":[71],"and":[72,98,101,135,182,197,211],"inter-node":[73,104],"balance.":[75],"We":[76,194],"refer":[77],"this":[79],"as":[80,201,203],"enclave":[81],"partitioning.":[82],"Our":[83],"parallelization":[84],"allows":[86,103],"same":[88],"shared-memory-level":[89],"code":[90,106,125,131],"used":[93],"on":[94,157],"also":[102],"communication":[105],"reused":[109],"during":[110],"CPU-accelerator":[111],"communication.":[112],"This":[113],"contrast":[116],"\"offload\"":[120],"model,":[121],"which":[123],"can":[126],"differ":[127],"significantly":[128],"from":[129],"form":[134],"programming":[136],"language.":[137],"Using":[138],"hybrid":[140],"MPI-OpenMP":[141],"implementation":[142],"acoustic-elastic":[145],"wave":[146],"propagation,":[147],"we":[148,169],"demonstrate":[149],"efficacy":[151],"proposed":[154],"heterogeneous,":[159],"Intel":[160],"R\u00ae":[161],"Xeon":[162],"Phi\u2122-accelerated":[163],"supercomputer":[164],"(Stampede).":[165],"With":[166],"our":[167],"approach":[168],"have":[170],"realized":[171],"speedups":[172],"up":[174],"5.78x":[176],"using":[177],"7th":[179],"discretization":[181,187],"6.88x":[183],"15th":[185],"relative":[188],"baseline,":[191],"pure-MPI":[192],"implementation.":[193],"present":[195],"strong":[196],"weak":[198],"scaling":[199],"results":[200],"well":[202],"individual":[204],"node":[205],"performance":[206],"illustrate":[208],"benefits":[210],"limits":[212],"scientific":[216],"computing.":[217]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}