{"id":"https://openalex.org/W2964336816","doi":"https://doi.org/10.1145/3229710.3229720","title":"High-Performance Sparse Matrix-Matrix Products on Intel KNL and Multicore Architectures","display_name":"High-Performance Sparse Matrix-Matrix Products on Intel KNL and Multicore Architectures","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2964336816","doi":"https://doi.org/10.1145/3229710.3229720","mag":"2964336816"},"language":"en","primary_location":{"id":"doi:10.1145/3229710.3229720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1454499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069048439","display_name":"Yusuke Nagasaka","orcid":"https://orcid.org/0009-0009-2204-2424"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Nagasaka","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan and Tokyo Institute of Technology, Department of Mathematical and Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan and Tokyo Institute of Technology, Department of Mathematical and Computing Sciences","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013984574","display_name":"Ariful Azad","orcid":"https://orcid.org/0000-0003-1332-8630"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariful Azad","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, California, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035719914","display_name":"Ayd\u0131n Bulu\u00e7","orcid":"https://orcid.org/0000-0001-7253-9038"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayd\u0131n Bulu\u00e7","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, California, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9970999956130981,"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":0.8401983976364136},{"id":"https://openalex.org/keywords/heap","display_name":"Heap (data structure)","score":0.8378815650939941},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7709343433380127},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6275250911712646},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6130784153938293},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5862968564033508},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5468605756759644},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5220606327056885},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4607343375682831},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4359031915664673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41836851835250854},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1212276816368103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401983976364136},{"id":"https://openalex.org/C134757568","wikidata":"https://www.wikidata.org/wiki/Q274089","display_name":"Heap (data structure)","level":2,"score":0.8378815650939941},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7709343433380127},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6275250911712646},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6130784153938293},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5862968564033508},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5468605756759644},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5220606327056885},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4607343375682831},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4359031915664673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41836851835250854},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1212276816368103},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3229710.3229720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1454499","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1454499","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1454499","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1454499","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W784772322","https://openalex.org/W1482680420","https://openalex.org/W1515144947","https://openalex.org/W1520511539","https://openalex.org/W1665157575","https://openalex.org/W1973918431","https://openalex.org/W1980282429","https://openalex.org/W2003840611","https://openalex.org/W2007259720","https://openalex.org/W2035080386","https://openalex.org/W2083257370","https://openalex.org/W2089437293","https://openalex.org/W2095249664","https://openalex.org/W2132202037","https://openalex.org/W2141380216","https://openalex.org/W2149454052","https://openalex.org/W2157174514","https://openalex.org/W2196186329","https://openalex.org/W2235832317","https://openalex.org/W2270203991","https://openalex.org/W2317543757","https://openalex.org/W2410432900","https://openalex.org/W2410461480","https://openalex.org/W2544527082","https://openalex.org/W2544965371","https://openalex.org/W2727953781","https://openalex.org/W2733486948","https://openalex.org/W2751658790","https://openalex.org/W2781869913","https://openalex.org/W2964336816","https://openalex.org/W3105937213"],"related_works":["https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2148563915","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W2796552083"],"abstract_inverted_index":{"Sparse":[0],"matrix-matrix":[1],"multiplication":[2],"(SpGEMM)":[3],"is":[4,9,57,190],"a":[5,45,89,94,176,195],"computational":[6],"primitive":[7],"that":[8,119,191],"widely":[10],"used":[11],"in":[12,145],"areas":[13],"ranging":[14],"from":[15,110,143],"traditional":[16],"numerical":[17],"applications":[18],"to":[19,178,205],"recent":[20],"big":[21],"data":[22],"analysis":[23,47],"and":[24,39,44,55,63,70,84,92,136,165,174],"machine":[25],"learning.":[26],"Although":[27],"many":[28],"SpGEMM":[29,97,182,193],"algorithms":[30,138,153],"have":[31],"been":[32],"proposed,":[33],"hardware":[34],"specific":[35],"optimizations":[36],"for":[37,184],"multi-":[38,83],"many-core":[40,85],"processors":[41],"are":[42,120,139,202],"lacking":[43],"detailed":[46],"of":[48,122,148,211],"their":[49,101],"performance":[50,102,197],"under":[51],"various":[52],"use":[53,117],"cases":[54,118,150],"matrices":[56],"not":[58,203],"available.":[59],"We":[60,99,168],"firstly":[61],"identify":[62],"mitigate":[64],"multiple":[65],"bottlenecks":[66],"with":[67,104,158],"memory":[68],"management":[69],"thread":[71],"scheduling":[72],"on":[73],"Intel":[74],"Xeon":[75],"Phi":[76],"(Knights":[77],"Landing":[78],"or":[79,131],"KNL).":[80],"Specifically":[81],"targeting":[82],"processors,":[86],"we":[87],"develop":[88],"hash-table-based":[90,192],"algorithm":[91,183],"optimize":[93],"heap-based":[95,137],"shared-memory":[96],"algorithm.":[98],"examine":[100],"together":[103],"other":[105,156],"publicly":[106],"available":[107],"codes.":[108],"Different":[109],"the":[111,146,149,155,180,200,212],"literature,":[112],"our":[113],"evaluation":[114,172],"also":[115],"includes":[116],"representative":[121],"real":[123],"graph":[124],"algorithms,":[125],"such":[126],"as":[127],"multi-source":[128],"breadth-first":[129],"search":[130],"triangle":[132],"counting.":[133],"Our":[134],"hash-table":[135],"showing":[140],"significant":[141,196],"speedups":[142],"libraries":[144],"majority":[147],"while":[151],"different":[152,159],"dominate":[154],"scenarios":[157],"matrix":[160],"size,":[161],"sparsity,":[162],"compression":[163],"factor":[164],"operation":[166],"type.":[167],"wrap":[169],"up":[170],"in-depth":[171],"results":[173],"make":[175],"recipe":[177],"give":[179],"best":[181],"target":[185],"scenario.":[186],"A":[187],"critical":[188],"finding":[189],"gets":[194],"boost":[198],"if":[199],"nonzeros":[201],"required":[204],"be":[206],"sorted":[207],"within":[208],"each":[209],"row":[210],"output":[213],"matrix.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}