{"id":"https://openalex.org/W4388581083","doi":"https://doi.org/10.1145/3624062.3624198","title":"Modelling Data Locality of Sparse Matrix-Vector Multiplication on the A64FX","display_name":"Modelling Data Locality of Sparse Matrix-Vector Multiplication on the A64FX","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581083","doi":"https://doi.org/10.1145/3624062.3624198"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624198","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090581401","display_name":"Sergej Breiter","orcid":"https://orcid.org/0009-0007-7742-1427"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sergej Breiter","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Germany"],"raw_orcid":"https://orcid.org/0009-0007-7742-1427","affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003537956","display_name":"James Trotter","orcid":"https://orcid.org/0000-0003-4498-020X"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"James D. Trotter","raw_affiliation_strings":["Simula Research Laboratory, Norway"],"raw_orcid":"https://orcid.org/0000-0003-4498-020X","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043839305","display_name":"Karl F\u00fcrlinger","orcid":"https://orcid.org/0000-0003-0398-4087"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karl F\u00fcrlinger","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0398-4087","affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090581401"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.2992,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52895459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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":0.8330700993537903},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8029855489730835},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7813283205032349},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7472085356712341},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.7050951719284058},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6493332386016846},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5681972503662109},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5571135878562927},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5103539824485779},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.46012449264526367},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.43041643500328064},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4295427203178406},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.41590583324432373},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4155653119087219},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.411201149225235},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34534305334091187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09126067161560059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330700993537903},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8029855489730835},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7813283205032349},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7472085356712341},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.7050951719284058},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6493332386016846},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5681972503662109},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5571135878562927},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5103539824485779},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.46012449264526367},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.43041643500328064},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4295427203178406},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.41590583324432373},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4155653119087219},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.411201149225235},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34534305334091187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09126067161560059},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624062.3624198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624198","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:126883","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-126883-9","pdf_url":"https://epub.ub.uni-muenchen.de/126883/1/3624062.3624198.pdf","source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"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":"NonPeerReviewed"}],"best_oa_location":{"id":"doi:10.1145/3624062.3624198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624198","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G5244242995","display_name":null,"funder_award_id":"270053","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320336863","display_name":"Leibniz-Rechenzentrum","ror":"https://ror.org/05558nw16"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581083.pdf","grobid_xml":"https://content.openalex.org/works/W4388581083.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W2032616619","https://openalex.org/W2035080386","https://openalex.org/W2135056392","https://openalex.org/W2155751237","https://openalex.org/W2164705534","https://openalex.org/W2284629249","https://openalex.org/W2987963343","https://openalex.org/W3035019560","https://openalex.org/W3097283637","https://openalex.org/W3097636320","https://openalex.org/W3190673640","https://openalex.org/W3205990959","https://openalex.org/W3206784402","https://openalex.org/W3206873289","https://openalex.org/W4200525217","https://openalex.org/W4205662846","https://openalex.org/W4230444879","https://openalex.org/W4242148175","https://openalex.org/W4251280768","https://openalex.org/W4362711800"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2546991807","https://openalex.org/W2734782074","https://openalex.org/W2538519144","https://openalex.org/W2121191383","https://openalex.org/W2535115842","https://openalex.org/W1505654810","https://openalex.org/W2076114130","https://openalex.org/W1584415117","https://openalex.org/W4252570104"],"abstract_inverted_index":{"One":[0],"of":[1,5,19,30,45,94,112,121,131],"the":[2,6,11,20,27,49,75,85,92,119,138],"novel":[3],"features":[4],"Fujitsu":[7],"A64FX":[8],"CPU":[9],"is":[10,33,68,135,141],"sector":[12,50,76,123],"cache.":[13],"This":[14,39],"feature":[15],"enables":[16],"hardware-supported":[17],"partitioning":[18],"L1":[21],"and":[22,25,82,103],"L2":[23,95],"caches":[24],"allows":[26],"programmer":[28],"control":[29],"which":[31],"partition":[32],"used":[34,55,69],"to":[35,47,52,70,79,83],"place":[36],"data":[37],"in.":[38],"paper":[40],"performs":[41],"an":[42],"in-depth":[43],"study":[44],"how":[46],"apply":[48],"cache":[51,77,86,96,124],"a":[53,110],"frequently":[54],"sparse":[56,114],"matrix-vector":[57],"multiplication":[58],"(SpMV)":[59],"kernel.":[60],"A":[61,128],"performance":[62],"model":[63,89],"based":[64],"on":[65,126],"reuse":[66,81],"analysis":[67],"better":[71],"understand":[72],"situations":[73],"where":[74],"leads":[78],"improved":[80],"predict":[84],"behavior.":[87],"The":[88],"correctly":[90],"predicts":[91],"number":[93],"misses":[97],"within":[98],"2\u20133":[99],"%":[100],"for":[101],"sequential":[102],"parallel":[104],"SpMV":[105],"with":[106],"48":[107],"threads":[108],"using":[109],"collection":[111],"490":[113],"matrices.":[115],"Further":[116],"experiments":[117],"show":[118],"effect":[120],"various":[122],"configurations":[125],"performance.":[127],"median":[129],"speedup":[130,140],"about":[132,142],"1.05":[133],"\u00d7":[134],"achieved,":[136],"whereas":[137],"maximum":[139],"1.6":[143],"\u00d7.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}