{"id":"https://openalex.org/W4407791963","doi":"https://doi.org/10.1177/10943420251319332","title":"Cache blocking of distributed-memory parallel matrix power kernels","display_name":"Cache blocking of distributed-memory parallel matrix power kernels","publication_year":2025,"publication_date":"2025-02-20","ids":{"openalex":"https://openalex.org/W4407791963","doi":"https://doi.org/10.1177/10943420251319332"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251319332","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251319332","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/10.1177/10943420251319332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113224779","display_name":"Dane C. Lacey","orcid":null},"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":"Dane Lacey","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0009-0008-5896-9646","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","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":false,"raw_author_name":"Christie Alappat","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4548-8727","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063117492","display_name":"F. F. Lange","orcid":"https://orcid.org/0000-0003-3389-1711"},"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":"Florian Lange","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3389-1711","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8723-2781","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), 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"]},{"id":"https://openalex.org/I36522303","display_name":"Universit\u00e4t Greifswald","ror":"https://ror.org/00r1edq15","country_code":"DE","type":"education","lineage":["https://openalex.org/I36522303"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Fehske","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","University of Greifswald","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","Institute of Physics, University of Greifswald, Greifswald, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"University of Greifswald","institution_ids":["https://openalex.org/I36522303"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Institute of Physics, University of Greifswald, Greifswald, Germany","institution_ids":["https://openalex.org/I36522303"]}]},{"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/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"]},{"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":["DE","NL"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Delft University of Technology","Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","Delft Institute of Applied Mathematics, Delft University of Technology, Netherlands","Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Delft Institute of Applied Mathematics, Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113224779"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02748836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"3","first_page":"385","last_page":"404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7188137769699097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6576958298683167},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6445314884185791},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5817043781280518},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2916146516799927}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7188137769699097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6576958298683167},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6445314884185791},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5817043781280518},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2916146516799927}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420251319332","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251319332","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"},{"id":"pmh:oai:open.fau.de:openfau/35972","is_oa":true,"landing_page_url":"https://open.fau.de/handle/openfau/35972","pdf_url":"https://open.fau.de/bitstreams/89c5ebb7-8de9-4c2e-a577-d6515d2c96ce/download","source":{"id":"https://openalex.org/S7407055110","display_name":"OPUS FAU - Online publication system of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/10943420251319332","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251319332","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":[{"id":"https://openalex.org/G5217879778","display_name":null,"funder_award_id":"16ME0708","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1867807796","https://openalex.org/W1961751213","https://openalex.org/W1967501281","https://openalex.org/W2002555321","https://openalex.org/W2005315955","https://openalex.org/W2010944731","https://openalex.org/W2018565448","https://openalex.org/W2035080386","https://openalex.org/W2043904766","https://openalex.org/W2101511474","https://openalex.org/W2132914434","https://openalex.org/W2145194992","https://openalex.org/W2165439482","https://openalex.org/W2264002775","https://openalex.org/W2809496910","https://openalex.org/W2957142384","https://openalex.org/W2995636625","https://openalex.org/W3001076433","https://openalex.org/W3005380678","https://openalex.org/W3039166741","https://openalex.org/W3090985951","https://openalex.org/W3122375428","https://openalex.org/W3140539246","https://openalex.org/W4226327117","https://openalex.org/W4312191554","https://openalex.org/W4402890182","https://openalex.org/W6726851532"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2353762239","https://openalex.org/W66314852","https://openalex.org/W2185938410","https://openalex.org/W2484966135"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"products":[2,41],"(SpMVs)":[3],"are":[4],"a":[5,97,106,171,195,215,228,241],"bottleneck":[6],"in":[7,50,161],"many":[8,51],"scientific":[9,223],"codes.":[10],"Due":[11],"to":[12,130,136,151,194,233,245],"the":[13,17,23,27,45,66,87,102,112,119,125,152,176,235],"heavy":[14],"strain":[15],"on":[16,208,247],"main":[18,73],"memory":[19,30,74,132],"interface":[20],"from":[21,72,221],"loading":[22],"sparse":[24,219],"matrix":[25,47,55,68,116],"and":[26,104,134,157,169,211],"possibly":[28],"irregular":[29],"access":[31],"pattern,":[32],"SpMV":[33,103,110],"typically":[34],"exhibits":[35],"low":[36],"arithmetic":[37],"intensity.":[38],"Repeating":[39],"these":[40],"multiple":[42,75],"times":[43],"with":[44,86,181],"same":[46,67],"is":[48,70,148],"required":[49],"algorithms.":[52],"This":[53],"so-called":[54],"power":[56],"kernel":[57],"(MPK)":[58],"provides":[59],"an":[60,77,182,251],"opportunity":[61,78],"for":[62,111,143,154],"data":[63,69,121,160,189],"reuse":[64,113],"since":[65],"loaded":[71],"times,":[76],"that":[79,174,186],"has":[80],"only":[81],"recently":[82],"been":[83],"exploited":[84],"successfully":[85],"Recursive":[88],"Algebraic":[89],"Coloring":[90],"Engine":[91],"(RACE).":[92],"Using":[93],"RACE,":[94],"one":[95],"considers":[96],"graph":[98],"based":[99],"formulation":[100],"of":[101,109,114,127,146,159,179,218,237,243,250],"employs":[105],"level-based":[107],"implementation":[108],"relevant":[115],"data.":[117],"However,":[118],"underlying":[120],"dependencies":[122,190],"have":[123],"restricted":[124],"use":[126],"this":[128,165],"concept":[129],"shared":[131],"parallelization":[133,145],"thus":[135],"single":[137],"compute":[138],"nodes.":[139],"Enabling":[140],"cache":[141],"blocking":[142],"distributed-memory":[144,197],"MPK":[147,204],"challenging":[149],"due":[150],"need":[153],"explicit":[155],"communication":[156,184],"synchronization":[158],"neighboring":[162],"levels.":[163],"In":[164],"work,":[166],"we":[167,226],"propose":[168],"implement":[170],"flexible":[172],"method":[173],"interleaves":[175],"cache-blocking":[177],"capabilities":[178],"RACE":[180],"MPI":[183],"scheme":[185],"fulfills":[187],"all":[188],"among":[191],"processes.":[192],"Compared":[193],"\u201ctraditional\u201d":[196],"parallel":[198],"MPK,":[199],"our":[200,238],"new":[201],"distributed":[202],"level-blocked":[203],"yields":[205],"substantial":[206],"speed-ups":[207],"modern":[209,229],"Intel":[210,252],"AMD":[212],"architectures":[213],"across":[214],"wide":[216],"range":[217],"matrices":[220],"various":[222],"applications.":[224],"Finally,":[225],"address":[227],"quantum":[230],"physics":[231],"problem":[232],"demonstrate":[234],"applicability":[236],"method,":[239],"achieving":[240],"speed-up":[242],"up":[244],"4\u00d7":[246],"832":[248],"cores":[249],"Sapphire":[253],"Rapids":[254],"cluster.":[255]},"counts_by_year":[],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}