{"id":"https://openalex.org/W4402890182","doi":"https://doi.org/10.1177/10943420241283828","title":"Algebraic temporal blocking for sparse iterative solvers on multi-core CPUs","display_name":"Algebraic temporal blocking for sparse iterative solvers on multi-core CPUs","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4402890182","doi":"https://doi.org/10.1177/10943420241283828"},"language":"en","primary_location":{"id":"doi:10.1177/10943420241283828","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241283828","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/10943420241283828","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058357790","display_name":"Christie Louis Alappat","orcid":"https://orcid.org/0000-0003-4548-8727"},"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":true,"raw_author_name":"Christie Alappat","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010377968","display_name":"Jonas Thies","orcid":"https://orcid.org/0000-0001-9231-9999"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jonas Thies","raw_affiliation_strings":["Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"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":"Georg Hager","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056729987","display_name":"Holger Fehske","orcid":"https://orcid.org/0000-0003-2146-8203"},"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":"Holger Fehske","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]},{"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","NL"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058357790"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":1.2156,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81165403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"39","issue":"2","first_page":"230","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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":0.9984999895095825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7920807600021362},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6657304763793945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6137783527374268},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.5553749203681946},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5324503183364868},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5092886686325073},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43378305435180664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35952574014663696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.277713418006897},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.04475247859954834}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7920807600021362},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6657304763793945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6137783527374268},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.5553749203681946},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5324503183364868},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5092886686325073},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43378305435180664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35952574014663696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.277713418006897},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.04475247859954834},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420241283828","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241283828","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/10943420241283828","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241283828","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1621069953","https://openalex.org/W1961194538","https://openalex.org/W1964987772","https://openalex.org/W1967501281","https://openalex.org/W1979360367","https://openalex.org/W1988888548","https://openalex.org/W2011024650","https://openalex.org/W2026991672","https://openalex.org/W2035080386","https://openalex.org/W2043904766","https://openalex.org/W2047344035","https://openalex.org/W2053486661","https://openalex.org/W2066692739","https://openalex.org/W2080090223","https://openalex.org/W2101511474","https://openalex.org/W2140153041","https://openalex.org/W2145194992","https://openalex.org/W2148038801","https://openalex.org/W2165439482","https://openalex.org/W2234212075","https://openalex.org/W2252007067","https://openalex.org/W2527856862","https://openalex.org/W2610122093","https://openalex.org/W2728074266","https://openalex.org/W2734368450","https://openalex.org/W2801307125","https://openalex.org/W2917550249","https://openalex.org/W2957142384","https://openalex.org/W2982670193","https://openalex.org/W3000281689","https://openalex.org/W3001076433","https://openalex.org/W3009302681","https://openalex.org/W3122375428","https://openalex.org/W3138063244","https://openalex.org/W3150173915","https://openalex.org/W3190565289","https://openalex.org/W4200226193","https://openalex.org/W4205471980","https://openalex.org/W4211094263","https://openalex.org/W4250530934","https://openalex.org/W4302416529","https://openalex.org/W4312191554"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2353762239","https://openalex.org/W2185938410","https://openalex.org/W2484966135","https://openalex.org/W2015050211","https://openalex.org/W2108990487","https://openalex.org/W1978276953","https://openalex.org/W2353899468"],"abstract_inverted_index":{"Sparse":[0],"linear":[1],"iterative":[2,165],"solvers":[3,16,239],"are":[4],"essential":[5],"for":[6,262],"many":[7],"large-scale":[8],"simulations.":[9],"Much":[10],"of":[11,14,24,30,36,97,128,146,159,197,228,237],"the":[12,21,49,81,92,125,133,157,169,173,178,216,225,229,235,249],"runtime":[13],"these":[15,43],"is":[17,60,221],"often":[18,222],"spent":[19],"in":[20,132,163,181,240],"implicit":[22],"evaluation":[23],"matrix":[25,71,86,100],"polynomials":[26],"via":[27],"a":[28,62,70,84,95,98,105,116,241,259],"sequence":[29],"sparse":[31,99,129,164,264],"matrix-vector":[32,130],"products.":[33],"A":[34],"variety":[35],"approaches":[37],"has":[38],"been":[39],"proposed":[40],"to":[41,65,73,79,148,199],"make":[42],"polynomial":[44,52,72,82,185],"evaluations":[45],"explicit":[46],"(i.e.,":[47],"fix":[48],"coefficients),":[50],"e.g.,":[51],"preconditioners":[53],"or":[54,115],"s-step":[55,183],"Krylov":[56],"methods.":[57],"Furthermore,":[58],"it":[59],"nowadays":[61],"popular":[63],"practice":[64],"approximate":[66],"triangular":[67],"solves":[68],"by":[69,224,256],"increase":[74,149],"parallelism.":[75],"Such":[76],"algorithms":[77,193,209],"allow":[78],"evaluate":[80],"using":[83,124],"so-called":[85],"power":[87,96],"kernel":[88],"(MPK),":[89],"which":[90,220],"computes":[91],"product":[93],"between":[94],"[Formula:":[101,108,112],"see":[102,109,113,201],"text]":[103,202],"and":[104,187,247,252],"dense":[106],"vector":[107],"text],":[110,114],"i.e.,":[111],"related":[117],"operation.":[118],"Recently":[119],"we":[120,140,155,176,194,233],"have":[121],"shown":[122],"that":[123],"level-based":[126],"formulation":[127],"multiplications":[131],"Recursive":[134],"Algebraic":[135],"Coloring":[136],"Engine":[137],"(RACE)":[138],"framework":[139],"can":[141],"perform":[142],"temporal":[143],"cache":[144],"blocking":[145],"MPK":[147],"its":[150],"performance.":[151],"In":[152],"this":[153,160],"work,":[154],"demonstrate":[156,177],"application":[158,236],"cache-blocking":[161,260],"optimization":[162],"solvers.":[166,265],"By":[167],"integrating":[168],"RACE":[170,257],"library":[171],"into":[172],"Trilinos":[174],"framework,":[175],"speedups":[179,196],"achieved":[180],"(preconditioned)":[182],"GMRES,":[184],"preconditioners,":[186],"algebraic":[188],"multigrid":[189],"(AMG).":[190],"For":[191,208],"MPK-dominated":[192],"achieve":[195],"up":[198,255],"3[Formula:":[200],"on":[203],"modern":[204],"multi-core":[205],"compute":[206],"nodes.":[207],"with":[210],"moderate":[211],"contributions":[212],"from":[213],"subspace":[214],"orthogonalization,":[215],"gain":[217],"reduces":[218],"significantly,":[219],"caused":[223],"insufficient":[226],"quality":[227],"orthogonalization":[230],"routines.":[231],"Finally,":[232],"showcase":[234],"RACE-accelerated":[238],"real-world":[242],"wind":[243],"turbine":[244],"simulation":[245],"(Nalu-Wind)":[246],"highlight":[248],"new":[250],"opportunities":[251],"perspectives":[253],"opened":[254],"as":[258],"technique":[261],"MPK-enabled":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}