{"id":"https://openalex.org/W2789352718","doi":"https://doi.org/10.1109/tpds.2018.2819672","title":"Massively Parallel Stencil Code Solver with Autonomous Adaptive Block Distribution","display_name":"Massively Parallel Stencil Code Solver with Autonomous Adaptive Block Distribution","publication_year":2018,"publication_date":"2018-03-26","ids":{"openalex":"https://openalex.org/W2789352718","doi":"https://doi.org/10.1109/tpds.2018.2819672","mag":"2789352718"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2819672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2819672","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5445/ir/1000081473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011009998","display_name":"Marco Berghoff","orcid":"https://orcid.org/0000-0003-4343-2228"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marco Berghoff","raw_affiliation_strings":["Steinbuch Centre for Computing (SCC), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany"],"affiliations":[{"raw_affiliation_string":"Steinbuch Centre for Computing (SCC), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003330064","display_name":"Ivan Kondov","orcid":"https://orcid.org/0000-0002-8794-616X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ivan Kondov","raw_affiliation_strings":["Steinbuch Centre for Computing (SCC), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany"],"affiliations":[{"raw_affiliation_string":"Steinbuch Centre for Computing (SCC), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025935876","display_name":"Johannes H\u00f6tzer","orcid":"https://orcid.org/0000-0001-9932-0562"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Hotzer","raw_affiliation_strings":["Institute for Applied Materials (IAM), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Applied Materials (IAM), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011009998"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.9863,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.72250287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"29","issue":"10","first_page":"2282","last_page":"2296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11087","display_name":"Solidification and crystal growth phenomena","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11087","display_name":"Solidification and crystal growth phenomena","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10049","display_name":"Magnetic properties of thin films","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9710000157356262,"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":0.8670623302459717},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8520631790161133},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7029119729995728},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6773781776428223},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6568622589111328},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6315512657165527},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6165929436683655},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4860966205596924},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47858238220214844},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4727174639701843},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.46543991565704346},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4639059901237488},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4463273882865906},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4299502968788147},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.41975319385528564},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41011151671409607},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27474573254585266},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.14410507678985596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670623302459717},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8520631790161133},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7029119729995728},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6773781776428223},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6568622589111328},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6315512657165527},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6165929436683655},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4860966205596924},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47858238220214844},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4727174639701843},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.46543991565704346},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4639059901237488},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4463273882865906},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4299502968788147},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41975319385528564},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41011151671409607},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27474573254585266},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.14410507678985596},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":3,"locations":[{"id":"doi:10.1109/tpds.2018.2819672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2819672","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000081473","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000081473","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE transactions on parallel and distributed systems, 29 (10), 2282-2296","raw_type":"doc-type:article"},{"id":"doi:10.5445/ir/1000081473","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000081473","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5445/ir/1000081473","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000081473","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311034","display_name":"Technische Universit\u00e4t Chemnitz","ror":"https://ror.org/00a208s56"},{"id":"https://openalex.org/F4320321752","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05"},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1540641082","https://openalex.org/W1548191435","https://openalex.org/W1570255162","https://openalex.org/W1636962080","https://openalex.org/W1762709353","https://openalex.org/W1923103968","https://openalex.org/W1966700002","https://openalex.org/W1969706687","https://openalex.org/W1970172627","https://openalex.org/W1978700654","https://openalex.org/W1978896773","https://openalex.org/W1997293122","https://openalex.org/W1999515131","https://openalex.org/W2002039787","https://openalex.org/W2002785668","https://openalex.org/W2004825628","https://openalex.org/W2005859257","https://openalex.org/W2006741141","https://openalex.org/W2007909139","https://openalex.org/W2014194090","https://openalex.org/W2015873351","https://openalex.org/W2020753345","https://openalex.org/W2039514558","https://openalex.org/W2046163855","https://openalex.org/W2056087726","https://openalex.org/W2056295840","https://openalex.org/W2060172487","https://openalex.org/W2079771357","https://openalex.org/W2080971404","https://openalex.org/W2084126569","https://openalex.org/W2087677612","https://openalex.org/W2102635728","https://openalex.org/W2104097935","https://openalex.org/W2107436920","https://openalex.org/W2111715635","https://openalex.org/W2121860230","https://openalex.org/W2149445607","https://openalex.org/W2153142220","https://openalex.org/W2211693886","https://openalex.org/W2212370034","https://openalex.org/W2245853462","https://openalex.org/W2271082361","https://openalex.org/W2275320771","https://openalex.org/W2276814379","https://openalex.org/W2326360667","https://openalex.org/W2332254154","https://openalex.org/W2412023093","https://openalex.org/W2596598754","https://openalex.org/W2766574842","https://openalex.org/W3104389750","https://openalex.org/W3105365024","https://openalex.org/W4206725542","https://openalex.org/W4230038347","https://openalex.org/W6634356361","https://openalex.org/W6675418917"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W1976044314","https://openalex.org/W2073684863","https://openalex.org/W2051596395","https://openalex.org/W2685773722","https://openalex.org/W2063646300","https://openalex.org/W1997392852","https://openalex.org/W2066041241","https://openalex.org/W854573101"],"abstract_inverted_index":{"In":[0],"the":[1,50,60,74,77,80,86,108,124,130,134,137,178,192,210,225,240,251,260],"last":[2],"decades,":[3],"simulations":[4],"have":[5],"been":[6],"established":[7],"in":[8,59,152,274],"several":[9],"fields":[10],"of":[11,30,41,52,56,62,67,79,110,121,173,184,213,247,277,283],"science":[12,279],"and":[13,32,49,142,157,228,270],"industry":[14],"to":[15,72,177,188,191,234,239,267,280],"study":[16],"various":[17,81],"phenomena":[18],"by":[19],"solving,":[20],"inter":[21,150],"alia,":[22,151],"partial":[23],"differential":[24],"equations.":[25],"For":[26,217],"an":[27],"efficient":[28],"use":[29,183],"current":[31],"future":[33],"high":[34,44,57],"performance":[35],"computing":[36,180,284],"systems,":[37],"with":[38],"many":[39],"thousands":[40],"computation":[42,138],"ranks,":[43],"node-level":[45],"performance,":[46],"scalable":[47],"communication,":[48],"omission":[51],"unnecessary":[53,145],"calculations":[54],"are":[55],"priority":[58],"development":[61],"new":[63],"solvers.":[64],"The":[65,182,205,245,262],"challenge":[66],"contemporary":[68],"simulation":[69,219],"applications":[70],"is":[71,123,159,256,264],"bridge":[73],"gap":[75],"between":[76],"scales":[78],"physical":[82],"processes.":[83],"We":[84],"introduce":[85],"NAStJA":[87,106,122],"framework,":[88],"a":[89,171,185],"block-based":[90],"MPI":[91],"parallel":[92],"solver":[93],"for":[94,250],"arbitrary":[95],"algorithms,":[96],"based":[97],"on":[98],"stencil":[99],"code":[100],"or":[101],"other":[102,275],"regular":[103],"grid":[104],"methods.":[105],"decomposes":[107],"domain":[109,132],"spatially":[111],"complex":[112],"structures":[113],"into":[114],"small":[115],"cuboid":[116],"blocks.":[117],"A":[118,165],"special":[119],"feature":[120],"dynamic":[125,252],"block":[126,254],"adaption":[127],"which":[128],"modifies":[129],"calculation":[131,226],"around":[133],"region":[135],"where":[136],"currently":[139],"takes":[140],"place,":[141],"hence":[143],"avoids":[144,195],"calculations.":[146],"This":[147],"often":[148],"occurs,":[149],"phase-field":[153,268],"simulations.":[154],"Block":[155],"creation":[156,255],"deletion":[158],"managed":[160],"autonomously":[161],"within":[162],"local":[163],"neighborhoods.":[164],"basic":[166],"load":[167],"balancing":[168],"mechanism":[169],"allows":[170],"re-distribution":[172],"newly":[174],"created":[175],"blocks":[176],"involved":[179],"ranks.":[181],"multi-hop":[186],"network,":[187],"distribute":[189],"information":[190],"entire":[193],"domain,":[194],"collective":[196],"all-gather":[197],"communications.":[198],"Thus,":[199],"we":[200,221],"can":[201,222,231,271],"demonstrate":[202],"excellent":[203],"scaling.":[204],"present":[206],"scaling":[207],"tests":[208],"substantiate":[209],"enormous":[211],"advantage":[212],"this":[214],"adaptive":[215],"method.":[216],"certain":[218],"scenarios,":[220],"show":[223],"that":[224],"effort":[227],"memory":[229],"consumption":[230],"be":[232,272],"reduced":[233],"only":[235],"3.5":[236],"percent,":[237],"compared":[238],"classical":[241],"full-domain":[242],"reference":[243],"simulation.":[244],"overhead":[246],"70-100":[248],"percent":[249],"adapting":[253],"significantly":[257],"lower":[258],"than":[259],"gain.":[261],"approach":[263],"not":[265],"restricted":[266],"simulations,":[269],"employed":[273],"domains":[276],"computational":[278],"exploit":[281],"sparsity":[282],"regions.":[285]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
