{"id":"https://openalex.org/W7119521942","doi":"https://doi.org/10.1145/3773656.3773690","title":"Task-decomposed Overlapped Preconditioner for Sustained Strong Scalability on Accelerated Exascale Systems","display_name":"Task-decomposed Overlapped Preconditioner for Sustained Strong Scalability on Accelerated Exascale Systems","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119521942","doi":"https://doi.org/10.1145/3773656.3773690"},"language":null,"primary_location":{"id":"doi:10.1145/3773656.3773690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773690","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773656.3773690","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060044772","display_name":"Niclas Jansson","orcid":"https://orcid.org/0000-0002-5020-1631"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Niclas Jansson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-5020-1631","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033686530","display_name":"Martin Karp","orcid":"https://orcid.org/0000-0003-3374-8093"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Martin Karp","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3374-8093","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009705616","display_name":"Szil\u00e1rd P\u00e1ll","orcid":"https://orcid.org/0000-0003-0603-5514"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Szil\u00e1rd P\u00e1ll","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0603-5514","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122371528","display_name":"Stefano Markidis","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0639-0639","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001997189","display_name":"Philipp Schlatter","orcid":"https://orcid.org/0000-0001-9627-5903"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Schlatter","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t (FAU) Erlangen\u2013N\u00fcrnberg, Erlangen, Germany and KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-9627-5903","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t (FAU) Erlangen\u2013N\u00fcrnberg, Erlangen, Germany and KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I181369854"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6747000217437744,"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":0.6747000217437744,"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":0.06809999793767929,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.03750000149011612,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.8884000182151794},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8429999947547913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4771000146865845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3828999996185303}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8884000182151794},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4771000146865845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3828999996185303},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773656.3773690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773690","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773656.3773690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773690","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2764286810","display_name":null,"funder_award_id":"2019-0472","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G3709336375","display_name":"Center of Excellence for Exascale CFD","funder_award_id":"101093393","funder_id":"https://openalex.org/F4320338444","funder_display_name":"HORIZON EUROPE Digital, Industry and Space"},{"id":"https://openalex.org/G783631743","display_name":"Innovative Algorithms for Applications on European Exascale Supercomputers","funder_award_id":"101118139","funder_id":"https://openalex.org/F4320338444","funder_display_name":"HORIZON EUROPE Digital, Industry and Space"}],"funders":[{"id":"https://openalex.org/F4320317161","display_name":"Swedish e-Science Research Centre","ror":"https://ror.org/01e59yk92"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320338444","display_name":"HORIZON EUROPE Digital, Industry and Space","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W152258552","https://openalex.org/W1559235864","https://openalex.org/W1984334096","https://openalex.org/W2003408966","https://openalex.org/W2047007012","https://openalex.org/W2969262004","https://openalex.org/W3120305453","https://openalex.org/W3173812025","https://openalex.org/W4321482611","https://openalex.org/W4388699080","https://openalex.org/W4392931976","https://openalex.org/W4405883336","https://openalex.org/W7109090520"],"related_works":[],"abstract_inverted_index":{"We":[0,53],"detail":[1],"our":[2,55],"work":[3],"on":[4,21,50,90,99],"improving":[5,68],"the":[6,15,34,65,69],"performance":[7,49,88],"and":[8,101],"scalability":[9,97],"of":[10,57],"key":[11],"numerical":[12],"methods":[13],"in":[14,29,83],"high-fidelity":[16],"spectral":[17],"element":[18],"code":[19],"Neko":[20],"accelerated":[22,91],"exascale":[23],"machines.":[24],"E\ufb03cient":[25],"preconditioners":[26],"are":[27],"essential":[28],"incompressible":[30],"fluid":[31],"dynamics;":[32],"however,":[33],"most":[35],"e\ufb03cient":[36],"method":[37],"(with":[38],"respect":[39],"to":[40,45,76],"convergence)":[41],"might":[42],"be":[43],"challenging":[44],"implement":[46],"with":[47,61,86],"good":[48],"an":[51],"accelerator.":[52],"present":[54],"development":[56],"a":[58],"GPU-optimised":[59],"preconditioner":[60,80],"task":[62],"overlapping":[63],"for":[64],"pressure-Poisson":[66],"equation,":[67],"preconditioner\u2019s":[70],"throughput":[71],"(in":[72],"TDoF/s)":[73],"by":[74],"close":[75],"60%.":[77],"The":[78],"new":[79],"is":[81],"explained":[82],"detail,":[84],"together":[85],"detailed":[87],"studies":[89,98],"Cray":[92],"EX":[93],"platforms,":[94],"including":[95],"strong":[96],"LUMI":[100],"Frontier.":[102]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-09T00:00:00"}
