{"id":"https://openalex.org/W2912054620","doi":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00038","title":"Merge-Based Parallel Sparse Matrix-Sparse Vector Multiplication with a Vector Architecture","display_name":"Merge-Based Parallel Sparse Matrix-Sparse Vector Multiplication with a Vector Architecture","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2912054620","doi":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00038","mag":"2912054620"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5100327725","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-3478-9260"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023686171","display_name":"Harumichi Yokoyama","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Harumichi Yokoyama","raw_affiliation_strings":["Syst. Platform Res. Labs., NEC Corp. Kawasaki, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Syst. Platform Res. Labs., NEC Corp. Kawasaki, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109538488","display_name":"Takuya Araki","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Araki","raw_affiliation_strings":["System Platform Research Laboratories, NEC Corporation, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"System Platform Research Laboratories, NEC Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":62},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"50"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984,"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":0.9984,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9981,"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/speedup","display_name":"Speedup","score":0.8263631},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.41151962}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8263631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575494},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6658431},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.62406665},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5371941},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.45571756},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.41151962},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35062677},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.32311976},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29560614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18805763},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1557692423","https://openalex.org/W1825216778","https://openalex.org/W1893178273","https://openalex.org/W1992011279","https://openalex.org/W2022219663","https://openalex.org/W2035080386","https://openalex.org/W2042545849","https://openalex.org/W2055497547","https://openalex.org/W2059966434","https://openalex.org/W2087507944","https://openalex.org/W2118585731","https://openalex.org/W2141380216","https://openalex.org/W2141662114","https://openalex.org/W2153635508","https://openalex.org/W2154111453","https://openalex.org/W2415007423","https://openalex.org/W2542072367","https://openalex.org/W2558631043","https://openalex.org/W2772734385","https://openalex.org/W2951113132","https://openalex.org/W2953657981","https://openalex.org/W4297789040"],"related_works":["https://openalex.org/W752783541","https://openalex.org/W4287593139","https://openalex.org/W4286856894","https://openalex.org/W4239424132","https://openalex.org/W4206811032","https://openalex.org/W3099313426","https://openalex.org/W2995605830","https://openalex.org/W2596457687","https://openalex.org/W2086123442","https://openalex.org/W1506547947"],"abstract_inverted_index":{"Sparse":[0],"matrix-sparse":[1],"vector":[2,30,48,51,89,112],"multiplication":[3,31],"(spMspV)":[4],"is":[5],"one":[6],"of":[7,69],"the":[8,67,77,110],"key":[9],"linear":[10],"algebra":[11],"primitives":[12],"for":[13,73,144,149],"various":[14],"graph":[15],"algorithms.":[16],"With":[17],"sparse":[18,28],"input/output":[19],"vectors,":[20],"it":[21,114,138],"has":[22],"superiority":[23,161],"in":[24,60,162],"computational":[25],"efficiency":[26],"over":[27,98],"matrix-dense":[29],"(spMV).":[32],"In":[33,66],"this":[34],"paper,":[35],"we":[36],"propose":[37],"a":[38,88,101,106,125,131,153],"merge-based":[39],"method":[40,86,157],"called":[41],"2DMerge":[42],"to":[43,130],"accelerate":[44],"spMspV":[45,103,127],"execution":[46],"on":[47,80,105,120,136],"architectures.":[49],"The":[50],"registers":[52],"are":[53],"effectively":[54],"utilized":[55],"by":[56],"merging":[57],"intermediate":[58],"results":[59,79],"both":[61],"horizontal":[62],"and":[63,93,100,117,124,147],"vertical":[64],"dimensions.":[65],"case":[68],"Breadth-first":[70],"search":[71],"(BFS)":[72],"finding":[74],"connected":[75],"components,":[76],"evaluation":[78],"large-scale":[81],"graphs":[82,151],"show":[83],"that":[84],"our":[85],"with":[87,152],"architecture":[90],"achieves":[91],"127X":[92],"50X":[94],"average":[95,121,142],"single-core":[96],"speedup":[97,143],"spMV":[99,123],"state-of-the-art":[102],"implementation":[104],"X86":[107],"architecture.":[108],"On":[109],"same":[111],"architecture,":[113],"runs":[115],"13X":[116],"9X":[118],"faster":[119],"than":[122],"baseline":[126],"implementation.":[128],"Compared":[129],"popular":[132],"computation":[133],"framework":[134],"GraphLab":[135],"X86,":[137],"also":[139,158],"realizes":[140],"11X":[141],"high-diameter":[145],"graphs,":[146],"23X":[148],"low-diameter":[150],"hybrid":[154],"strategy.":[155],"Our":[156],"shows":[159],"performance":[160],"Bellman-Ford":[163],"single-source-shortest-path":[164],"(SSSP)":[165],"algorithm.":[166]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2912054620","counts_by_year":[],"updated_date":"2024-12-13T14:31:08.094873","created_date":"2019-02-21"}