{"id":"https://openalex.org/W4312191554","doi":"https://doi.org/10.1109/tpds.2022.3223512","title":"Level-Based Blocking for Sparse Matrices: Sparse Matrix-Power-Vector Multiplication","display_name":"Level-Based Blocking for Sparse Matrices: Sparse Matrix-Power-Vector Multiplication","publication_year":2022,"publication_date":"2022-11-21","ids":{"openalex":"https://openalex.org/W4312191554","doi":"https://doi.org/10.1109/tpds.2022.3223512"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3223512","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3223512","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9996310/09956740.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/9996310/09956740.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058357790","display_name":"Christie Louis Alappat","orcid":"https://orcid.org/0000-0003-4548-8727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christie Alappat","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4548-8727","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8723-2781","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017590193","display_name":"Olaf Schenk","orcid":"https://orcid.org/0000-0001-8636-1023"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olaf Schenk","raw_affiliation_strings":["Institute of Computing at Faculty of Informatics, Universit&#x00E0; della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8636-1023","affiliations":[{"raw_affiliation_string":"Institute of Computing at Faculty of Informatics, Universit&#x00E0; della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7371-3026","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center, Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0458,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92199266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"34","issue":"2","first_page":"581","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.750378429889679},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7164400815963745},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6965095400810242},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5126437544822693},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5031794905662537},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.49205130338668823},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45401373505592346},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4429357945919037},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42260679602622986},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36390161514282227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18454396724700928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750378429889679},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7164400815963745},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6965095400810242},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5126437544822693},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5031794905662537},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.49205130338668823},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45401373505592346},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4429357945919037},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42260679602622986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36390161514282227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18454396724700928},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2022.3223512","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3223512","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9996310/09956740.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2205.01598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.01598","pdf_url":"https://arxiv.org/pdf/2205.01598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/tpds.2022.3223512","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3223512","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9996310/09956740.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312191554.pdf","grobid_xml":"https://content.openalex.org/works/W4312191554.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1506424797","https://openalex.org/W1575701986","https://openalex.org/W1590523881","https://openalex.org/W1605308404","https://openalex.org/W1867807796","https://openalex.org/W1907157228","https://openalex.org/W1967501281","https://openalex.org/W1971343078","https://openalex.org/W1997147891","https://openalex.org/W2007152167","https://openalex.org/W2010944731","https://openalex.org/W2025564310","https://openalex.org/W2032032242","https://openalex.org/W2035080386","https://openalex.org/W2035701183","https://openalex.org/W2043904766","https://openalex.org/W2047450102","https://openalex.org/W2066692739","https://openalex.org/W2101511474","https://openalex.org/W2104512032","https://openalex.org/W2105685140","https://openalex.org/W2126004407","https://openalex.org/W2153580689","https://openalex.org/W2154590891","https://openalex.org/W2162630236","https://openalex.org/W2165439482","https://openalex.org/W2167868137","https://openalex.org/W2221817300","https://openalex.org/W2234212075","https://openalex.org/W2490296388","https://openalex.org/W2570841452","https://openalex.org/W2610122093","https://openalex.org/W2898099374","https://openalex.org/W2914631005","https://openalex.org/W2957142384","https://openalex.org/W2962978274","https://openalex.org/W2995636625","https://openalex.org/W3001076433","https://openalex.org/W3005380678","https://openalex.org/W3099448935","https://openalex.org/W3122375428","https://openalex.org/W3132357455","https://openalex.org/W3145241477","https://openalex.org/W3146331811","https://openalex.org/W4253426709","https://openalex.org/W6635603319","https://openalex.org/W6682848092","https://openalex.org/W6684509964","https://openalex.org/W6689006381","https://openalex.org/W6998938212","https://openalex.org/W7008672335"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"The":[0],"multiplication":[1,37],"of":[2,38,54,91,115,143,150,156,166,175,192],"a":[3,7,12,39,44,52,110,188],"sparse":[4,40,92,104],"matrix":[5,41,73,93,105,130,145],"with":[6,43],"dense":[8,45],"vector":[9,46],"(SpMV)":[10],"is":[11,22,48,141],"key":[13],"component":[14],"in":[15,58,154],"many":[16],"numerical":[17,33,199],"schemes":[18,34,200],"and":[19,61,124,132,147,159,172,179,195,209],"its":[20],"performance":[21,60,170],"known":[23],"to":[24,65,88,121,133,177,182],"be":[25],"severely":[26],"limited":[27],"by":[28,70],"main":[29],"memory":[30],"access.":[31],"Several":[32],"require":[35],"the":[36,63,67,72,82,96,100,103,129,144,164],"polynomial":[42,97,207],"which":[47],"typically":[49],"implemented":[50],"as":[51],"sequence":[53],"SpMVs.":[55],"This":[56],"results":[57],"low":[59],"ignores":[62],"potential":[64],"increase":[66],"arithmetic":[68],"intensity":[69],"reusing":[71],"data":[74,94,131],"from":[75,215],"cache.":[76],"In":[77,99],"this":[78],"work":[79],"we":[80,106],"use":[81],"recursive":[83],"algebraic":[84],"coloring":[85],"engine":[86],"(RACE)":[87],"enable":[89],"blocking":[90],"across":[95],"computations.":[98],"graph":[101],"representing":[102],"form":[107],"levels":[108,117],"using":[109,169],"breadth-first":[111],"search.":[112],"Locality":[113],"relations":[114],"these":[116],"are":[118],"then":[119],"used":[120],"improve":[122],"spatial":[123],"temporal":[125],"locality":[126],"when":[127],"accessing":[128],"implement":[134],"an":[135,183],"efficient":[136],"multithreaded":[137],"parallelization.":[138],"Our":[139],"approach":[140],"independent":[142],"structure":[146],"avoids":[148],"shortcomings":[149],"existing":[151],"\u201cblocking\u201d":[152],"strategies":[153],"terms":[155],"hardware":[157],"efficiency":[158],"parallelization":[160],"overhead.":[161],"We":[162],"quantify":[163],"quality":[165],"our":[167,216],"implementation":[168],"modelling":[171],"demonstrate":[173],"speedups":[174],"up":[176],"3\u00d7":[178],"5\u00d7":[180],"compared":[181],"optimal":[184],"SpMV-based":[185],"baseline":[186],"on":[187],"single":[189],"multicore":[190],"chip":[191],"recent":[193],"Intel":[194],"AMD":[196],"architectures.":[197],"Various":[198],"like":[201],"<inline-formula><tex-math":[202],"notation=\"LaTeX\">$s$</tex-math></inline-formula>":[203],"-step":[204],"Krylov":[205],"solvers,":[206],"preconditioners":[208],"power":[210],"clustering":[211],"algorithms":[212],"will":[213],"benefit":[214],"development.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}