{"id":"https://openalex.org/W1996529644","doi":"https://doi.org/10.1145/1375527.1375558","title":"Adaptive runtime tuning of parallel sparse matrix-vector multiplication on distributed memory systems","display_name":"Adaptive runtime tuning of parallel sparse matrix-vector multiplication on distributed memory systems","publication_year":2008,"publication_date":"2008-06-07","ids":{"openalex":"https://openalex.org/W1996529644","doi":"https://doi.org/10.1145/1375527.1375558","mag":"1996529644"},"language":"en","primary_location":{"id":"doi:10.1145/1375527.1375558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090962911","display_name":"Seyong Lee","orcid":"https://orcid.org/0000-0001-8872-4932"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seyong Lee","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045622261","display_name":"Rudolf Eigenmann","orcid":"https://orcid.org/0000-0003-1651-827X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudolf Eigenmann","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090962911"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":3.1892,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91958841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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":0.8573055863380432},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7811353206634521},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6134475469589233},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5793976187705994},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5774725675582886},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5366607904434204},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.500835657119751},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.47788989543914795},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4751030206680298},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3765418529510498},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.0902239978313446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8573055863380432},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7811353206634521},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6134475469589233},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5793976187705994},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5774725675582886},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5366607904434204},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.500835657119751},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.47788989543914795},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4751030206680298},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3765418529510498},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0902239978313446},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1375527.1375558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1344","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/343","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W42677130","https://openalex.org/W112345847","https://openalex.org/W1581205252","https://openalex.org/W1603927537","https://openalex.org/W1966476169","https://openalex.org/W1990832096","https://openalex.org/W2040836065","https://openalex.org/W2099507400","https://openalex.org/W2099763292","https://openalex.org/W2105908643","https://openalex.org/W2113734481","https://openalex.org/W2123291824","https://openalex.org/W2130289795","https://openalex.org/W2142184646","https://openalex.org/W2150896015","https://openalex.org/W2163365612","https://openalex.org/W2163501979","https://openalex.org/W2165575435"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2026512611","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"(SpMV)":[2],"multiplication":[3,17],"is":[4,18],"a":[5,28,110,138],"widely":[6],"used":[7],"kernel":[8],"in":[9],"scientific":[10],"applications.":[11],"In":[12,63],"these":[13],"applications,":[14],"the":[15,55,74,105],"SpMV":[16],"usually":[19],"deeply":[20],"nested":[21],"within":[22],"multiple":[23],"loops":[24],"and":[25,97,114],"thus":[26],"executed":[27],"large":[29],"number":[30],"of":[31],"times.":[32],"We":[33],"have":[34],"observed":[35],"that":[36,123],"there":[37],"can":[38],"be":[39,58],"significant":[40],"performance":[41,50,76],"variability,":[42],"due":[43],"to":[44,72,132],"irregular":[45],"memory":[46,79],"access":[47],"patterns.":[48],"Static":[49],"optimizations":[51],"are":[52],"difficult":[53],"because":[54],"patterns":[56],"may":[57],"known":[59],"only":[60],"at":[61,89],"runtime.":[62],"this":[64],"paper,":[65],"we":[66],"propose":[67],"adaptive":[68,82],"runtime":[69,90,99,125],"tuning":[70,126],"mechanisms":[71],"improve":[73],"parallel":[75,141],"on":[77,95,118,135,143],"distributed":[78,144],"systems.":[80],"Our":[81],"iteration-to-process":[83],"mapping":[84],"mechanism":[85],"balances":[86],"computational":[87],"load":[88],"with":[91,146],"negligible":[92],"overhead":[93],"(1%":[94],"average),":[96],"our":[98,124],"communication":[100,107],"selection":[101],"algorithm":[102,142],"searches":[103],"for":[104,109],"best":[106],"method":[108],"given":[111],"data":[112],"distribution":[113],"mapping.":[115],"Actual":[116],"runs":[117],"26":[119],"real":[120],"matrices":[121],"show":[122],"system":[127],"reduces":[128],"execution":[129],"time":[130],"up":[131],"68.8%":[133],"(30.9%":[134],"average)":[136],"over":[137],"base":[139],"block-distributed":[140],"systems":[145],"32":[147],"nodes.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}