{"id":"https://openalex.org/W2539342202","doi":"https://doi.org/10.1109/tpds.2016.2618791","title":"Semi-External Memory Sparse Matrix Multiplication for Billion-Node Graphs","display_name":"Semi-External Memory Sparse Matrix Multiplication for Billion-Node Graphs","publication_year":2016,"publication_date":"2016-10-19","ids":{"openalex":"https://openalex.org/W2539342202","doi":"https://doi.org/10.1109/tpds.2016.2618791","mag":"2539342202"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2618791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2618791","pdf_url":null,"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":null,"license_id":null,"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":"green","oa_url":"https://arxiv.org/pdf/1602.02864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Da Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Da Zheng","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Disa Mhembere","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Disa Mhembere","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vince Lyzinski","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vince Lyzinski","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joshua T. Vogelstein","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua T. Vogelstein","raw_affiliation_strings":["Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Carey E. Priebe","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carey E. Priebe","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":null,"display_name":"Randal Burns","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randal Burns","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.8583,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90591956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"28","issue":"5","first_page":"1470","last_page":"1483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.6589000225067139,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.6589000225067139,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.19750000536441803,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.027499999850988388,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/sparse-matrix","display_name":"Sparse matrix","score":0.7818999886512756},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6711999773979187},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5831999778747559},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5504000186920166},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5489000082015991},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4140999913215637},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.39149999618530273}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7818999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755299985408783},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7389000058174133},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6711999773979187},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5489000082015991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2016.2618791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2618791","pdf_url":null,"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":null,"license_id":null,"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:1602.02864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.02864","pdf_url":"https://arxiv.org/pdf/1602.02864","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":"pmh:oai:arXiv.org:1602.02864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.02864","pdf_url":"https://arxiv.org/pdf/1602.02864","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1419607908","display_name":null,"funder_award_id":"ACI-1261715","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6181935752","display_name":null,"funder_award_id":"N66001-15-C-4041","funder_id":"https://openalex.org/F4320337532","funder_display_name":"Space and Naval Warfare Systems Command"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337532","display_name":"Space and Naval Warfare Systems Command","ror":"https://ror.org/000ztjy10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W284798019","https://openalex.org/W1482680420","https://openalex.org/W1506690472","https://openalex.org/W1975283025","https://openalex.org/W1978979183","https://openalex.org/W1982056505","https://openalex.org/W1985312666","https://openalex.org/W1987349051","https://openalex.org/W1990832096","https://openalex.org/W2005423095","https://openalex.org/W2011655084","https://openalex.org/W2022916138","https://openalex.org/W2037726512","https://openalex.org/W2043715315","https://openalex.org/W2044782015","https://openalex.org/W2061919600","https://openalex.org/W2066463080","https://openalex.org/W2066636486","https://openalex.org/W2068015060","https://openalex.org/W2073955633","https://openalex.org/W2078206000","https://openalex.org/W2083036673","https://openalex.org/W2086666883","https://openalex.org/W2093053744","https://openalex.org/W2093529653","https://openalex.org/W2100235918","https://openalex.org/W2101196063","https://openalex.org/W2103656237","https://openalex.org/W2117686912","https://openalex.org/W2119571791","https://openalex.org/W2130289795","https://openalex.org/W2134237243","https://openalex.org/W2139694940","https://openalex.org/W2142827986","https://openalex.org/W2143705506","https://openalex.org/W2153622543","https://openalex.org/W2167927436","https://openalex.org/W2483598939","https://openalex.org/W6601271094","https://openalex.org/W6603201521","https://openalex.org/W6606610260","https://openalex.org/W6628445530","https://openalex.org/W6636599907","https://openalex.org/W6638659379","https://openalex.org/W6640836205","https://openalex.org/W6653919851","https://openalex.org/W6655383422","https://openalex.org/W6678914686","https://openalex.org/W6680012447","https://openalex.org/W6685693927","https://openalex.org/W6693961709"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix":[1,25,33,35,49,144,175],"multiplication":[2,26,36],"is":[3],"traditionally":[4],"performed":[5],"in":[6,38,56,119],"memory":[7,16,28,41,120],"and":[8,53,75,78,173],"scales":[9,79],"to":[10,80,122,166],"large":[11,65,93],"matrices":[12,55],"using":[13,107],"the":[14,47,70,85,102,124,142,184,187],"distributed":[15,103],"of":[17,73,87,105,126,137,157,186],"multiple":[18],"nodes.":[19],"In":[20],"contrast,":[21],"we":[22,45],"scale":[23],"sparse":[24,32,48],"beyond":[27,84],"capacity":[29],"by":[30],"implementing":[31],"dense":[34,54,143],"(SpMM)":[37],"a":[39,91],"semi-external":[40],"(SEM)":[42],"fashion;":[43],"i.e.,":[44],"keep":[46],"on":[50,90,129,139,159],"commodity":[51],"SSDs":[52],"memory.":[57,88],"Our":[58],"SEM-SpMM":[59,97,131],"incorporates":[60],"many":[61],"in-memory":[62,71],"optimizations":[63],"for":[64],"power-law":[66],"graphs.":[67],"It":[68],"outperforms":[69],"implementations":[72,104,181],"Trilinos":[74,106],"Intel":[76],"MKL":[77],"billion-node":[81],"graphs,":[82],"far":[83],"limitations":[86],"Furthermore,":[89],"single":[92],"parallel":[94],"machine,":[95],"our":[96,117,164,179],"operates":[98],"as":[99,101,110],"fast":[100],"five":[108],"times":[109],"much":[111],"processing":[112],"power.":[113],"We":[114,162],"also":[115],"run":[116],"implementation":[118],"(IM-SpMM)":[121],"quantify":[123],"overhead":[125],"keeping":[127],"data":[128,169],"SSDs.":[130],"achieves":[132,151],"almost":[133],"100":[134],"percent":[135,155],"performance":[136,156],"IM-SpMM":[138,158],"graphs":[140],"when":[141],"has":[145],"more":[146],"than":[147],"four":[148],"columns;":[149],"it":[150],"at":[152],"least":[153],"65":[154],"all":[160],"inputs.":[161],"apply":[163],"SpMM":[165],"three":[167],"important":[168],"analysis":[170],"tasks-PageRank,":[171],"eigensolving,":[172],"non-negative":[174],"factorization-and":[176],"show":[177],"that":[178],"SEM":[180],"significantly":[182],"advance":[183],"state":[185],"art.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2016-10-28T00:00:00"}