{"id":"https://openalex.org/W2952622072","doi":"https://doi.org/10.1145/3330345.3330358","title":"Using performance models to understand scalable Krylov solver performance at scale for structured grid problems","display_name":"Using performance models to understand scalable Krylov solver performance at scale for structured grid problems","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2952622072","doi":"https://doi.org/10.1145/3330345.3330358","mag":"2952622072"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330358","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330358","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330358","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330358","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030692374","display_name":"Paul R. Eller","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul R. Eller","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Gropp","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8474301695823669},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.721424400806427},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.669140636920929},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5119946599006653},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5080897808074951},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5032472014427185},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4856497049331665},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48034775257110596},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.4759920835494995},{"id":"https://openalex.org/keywords/network-performance","display_name":"Network performance","score":0.4412631392478943},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43466633558273315},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42255908250808716},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41540688276290894},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3725203573703766},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2579880952835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474301695823669},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.721424400806427},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.669140636920929},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5119946599006653},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5080897808074951},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5032472014427185},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4856497049331665},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48034775257110596},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.4759920835494995},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.4412631392478943},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43466633558273315},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42255908250808716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41540688276290894},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3725203573703766},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2579880952835083},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","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},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330345.3330358","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330358","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330358","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3330345.3330358","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330358","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330358","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1340859922","display_name":null,"funder_award_id":"DE-FG02-13ER26138/DE-SC0010049","funder_id":"https://openalex.org/F4320337674","funder_display_name":"Wind Energy Technologies Office"},{"id":"https://openalex.org/G6476835034","display_name":null,"funder_award_id":"OCI 07-25070","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7186324567","display_name":null,"funder_award_id":"DE-FG02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8684078510","display_name":null,"funder_award_id":"DE-FG02","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"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337144","display_name":"National Supercomputing Center, Korea Institute of Science and Technology Information","ror":null},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320337674","display_name":"Wind Energy Technologies Office","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952622072.pdf","grobid_xml":"https://content.openalex.org/works/W2952622072.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W90568776","https://openalex.org/W1569090332","https://openalex.org/W1629601946","https://openalex.org/W2000882268","https://openalex.org/W2009223344","https://openalex.org/W2021856036","https://openalex.org/W2040881475","https://openalex.org/W2042120213","https://openalex.org/W2071336726","https://openalex.org/W2079472602","https://openalex.org/W2080225225","https://openalex.org/W2096714979","https://openalex.org/W2102061396","https://openalex.org/W2115020004","https://openalex.org/W2117663029","https://openalex.org/W2154731982","https://openalex.org/W2164144057","https://openalex.org/W2165102815","https://openalex.org/W2165808215","https://openalex.org/W2241634195","https://openalex.org/W2300227969","https://openalex.org/W2316564661","https://openalex.org/W2490366892","https://openalex.org/W2499705876","https://openalex.org/W2535045667","https://openalex.org/W2564542575","https://openalex.org/W2767461568","https://openalex.org/W2783685059","https://openalex.org/W2788190323","https://openalex.org/W2805739788","https://openalex.org/W2891730571","https://openalex.org/W2950049801","https://openalex.org/W2991720310","https://openalex.org/W3103554130","https://openalex.org/W3201199382","https://openalex.org/W4229929217"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2151092287"],"abstract_inverted_index":{"Krylov":[0,91],"solvers":[1,92],"are":[2],"key":[3],"kernels":[4,95,156],"in":[5],"many":[6],"large-scale":[7],"science":[8],"and":[9,36,62,83,93,99,126,144,147,163,169],"engineering":[10],"applications":[11],"for":[12,90,102],"solving":[13],"sparse":[14],"linear":[15],"systems.":[16],"Applications":[17],"running":[18],"at":[19,60,81,106,182],"scale":[20,61,82,183],"can":[21,43,185],"experience":[22],"significant":[23],"slowdown":[24],"due":[25],"to":[26,55,87,117,123,154,179],"factors":[27,48],"such":[28],"as":[29],"network":[30,34,114,120,139,141],"congestion,":[31,33,140],"off-node":[32],"distance,":[35,142],"performance":[37,63,75,111,115,125,131,181],"variation":[38,64],"across":[39,65],"processes.":[40],"Performance":[41],"models":[42,53,76,86,132,151],"help":[44],"us":[45,153,172],"better":[46,175],"understand":[47],"limiting":[49],"performance,":[50],"however":[51],"simple":[52],"fail":[54],"capture":[56,78,134],"slowdowns":[57],"often":[58],"occurring":[59],"multiple":[66],"runs":[67],"of":[68,130,138,177,190],"the":[69,128,135],"same":[70],"code.":[71],"This":[72],"work":[73],"develops":[74],"that":[77,133,184],"behavior":[79,121],"found":[80],"uses":[84],"these":[85],"guide":[88,127,152],"optimizations":[89],"related":[94],"using":[96,157],"both":[97],"blocking":[98],"non-blocking":[100],"communication":[101,143],"structured":[103],"grid":[104],"problems":[105],"scale.":[107],"We":[108],"use":[109],"detailed":[110],"analysis":[112,170],"with":[113,173],"counters":[116],"show":[118],"how":[119,178],"relates":[122],"observed":[124],"development":[129],"runtime":[136],"impact":[137],"computation":[145],"overlap,":[146],"process":[148],"mappings.":[149],"These":[150],"optimize":[155],"MPI":[158],"protocol":[159],"changes,":[160],"node-aware":[161],"communication,":[162],"topology-aware":[164],"communication.":[165],"The":[166],"resulting":[167],"tools":[168],"provide":[171],"a":[174,187],"understanding":[176],"improve":[180],"benefit":[186],"wider":[188],"range":[189],"applications.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}