{"id":"https://openalex.org/W2979747168","doi":"https://doi.org/10.1145/3352460.3358330","title":"Efficient SpMV Operation for Large and Highly Sparse Matrices using Scalable Multi-way Merge Parallelization","display_name":"Efficient SpMV Operation for Large and Highly Sparse Matrices using Scalable Multi-way Merge Parallelization","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2979747168","doi":"https://doi.org/10.1145/3352460.3358330","mag":"2979747168"},"language":"en","primary_location":{"id":"doi:10.1145/3352460.3358330","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3352460.3358330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture","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/A5013781918","display_name":"Fazle Sadi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fazle Sadi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051704492","display_name":"Joe Sweeney","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joe Sweeney","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019607600","display_name":"Tze Meng Low","orcid":"https://orcid.org/0000-0002-5179-8249"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tze Meng Low","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019376179","display_name":"James C. Hoe","orcid":"https://orcid.org/0000-0002-9302-5287"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James C. Hoe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033242808","display_name":"Larry Pileggi","orcid":"https://orcid.org/0000-0002-8605-8240"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Pileggi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Franchetti","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":7.2516,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.97414339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"347","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8558925986289978},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7236713767051697},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6229518055915833},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6123687624931335},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.5688363909721375},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.45756465196609497},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4540945887565613},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3976377844810486},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.367609441280365},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33826836943626404},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2757018208503723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558925986289978},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7236713767051697},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6229518055915833},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6123687624931335},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.5688363909721375},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.45756465196609497},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4540945887565613},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3976377844810486},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.367609441280365},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33826836943626404},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2757018208503723},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3352460.3358330","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3352460.3358330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W131619556","https://openalex.org/W1964471912","https://openalex.org/W1993284846","https://openalex.org/W2028441625","https://openalex.org/W2030866898","https://openalex.org/W2035080386","https://openalex.org/W2038142281","https://openalex.org/W2071819510","https://openalex.org/W2072974923","https://openalex.org/W2075960179","https://openalex.org/W2098161986","https://openalex.org/W2108540054","https://openalex.org/W2112313615","https://openalex.org/W2114378634","https://openalex.org/W2123845384","https://openalex.org/W2128853364","https://openalex.org/W2134237243","https://openalex.org/W2141389982","https://openalex.org/W2148570406","https://openalex.org/W2150909864","https://openalex.org/W2168371416","https://openalex.org/W2270781678","https://openalex.org/W2287057303","https://openalex.org/W2508353373","https://openalex.org/W2566870951","https://openalex.org/W2573305191","https://openalex.org/W2575908230","https://openalex.org/W2597839305","https://openalex.org/W2733107613","https://openalex.org/W2757836131","https://openalex.org/W2766269404","https://openalex.org/W2766681651","https://openalex.org/W2884144908","https://openalex.org/W2890524446","https://openalex.org/W2963371212","https://openalex.org/W3142570770","https://openalex.org/W3143219376","https://openalex.org/W3146763006","https://openalex.org/W4241140669","https://openalex.org/W4251454195","https://openalex.org/W4285719527","https://openalex.org/W6793127252"],"related_works":["https://openalex.org/W1509155667","https://openalex.org/W2518118925","https://openalex.org/W3208151864","https://openalex.org/W1564576805","https://openalex.org/W4254372399","https://openalex.org/W2293771254","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W2914631005"],"abstract_inverted_index":{"The":[0],"importance":[1],"of":[2,21,31,62,83,137,161,190,203],"Sparse":[3],"Matrix":[4],"dense":[5],"Vector":[6],"multiplication":[7],"(SpMV)":[8],"operation":[9,42],"in":[10,165],"graph":[11],"analytics":[12],"and":[13,127,152,178,198,214],"numerous":[14],"scientific":[15],"applications":[16],"has":[17],"led":[18],"to":[19,27,56,67,148],"development":[20],"custom":[22,195],"accelerators":[23],"that":[24,95],"are":[25,168],"intended":[26],"over-come":[28],"the":[29,134],"difficulties":[30,76],"sparse":[32,106],"data":[33,84,145],"operations":[34],"on":[35,43,59,81,99],"general":[36],"purpose":[37],"architectures.":[38],"However,":[39],"efficient":[40],"SpMV":[41,141],"large":[44,101,126,159],"problem":[45],"(i.e.":[46],"working":[47],"set":[48],"exceeds":[49],"on-chip":[50,114],"storage)":[51],"is":[52,133,172],"severely":[53],"constrained":[54],"due":[55],"strong":[57],"dependence":[58],"limited":[60],"amount":[61],"fast":[63,115],"random":[64],"access":[65],"memory":[66,116],"scale.":[68],"Additionally,":[69,143],"unstructured":[70],"matrix":[71],"with":[72,111,157,174],"high":[73,128,139],"sparsity":[74],"pose":[75],"as":[77],"most":[78],"solutions":[79,197],"rely":[80],"exploitation":[82],"locality.":[85],"This":[86,170],"work":[87],"presents":[88],"an":[89,188],"algorithm":[90],"co-optimized":[91],"scalable":[92],"hardware":[93,196],"architecture":[94],"can":[96],"efficiently":[97],"operate":[98],"very":[100],"(~billion":[102],"nodes)":[103],"and/or":[104],"highly":[105],"(avg.":[107],"degree":[108],"<10)":[109],"graphs":[110],"significantly":[112],"less":[113],"than":[117,187,200],"existing":[118],"solutions.":[119],"A":[120],"novel":[121],"parallelization":[122],"methodology":[123],"for":[124,155,211],"implementing":[125],"throughput":[129],"multi-way":[130],"merge":[131],"network":[132],"key":[135],"enabler":[136],"this":[138],"performance":[140,213],"accelerator.":[142],"a":[144],"compression":[146],"scheme":[147],"reduce":[149],"off-chip":[150],"traffic":[151],"special":[153],"computation":[154],"nodes":[156],"exceptionally":[158],"number":[160],"edges,":[162],"commonly":[163],"found":[164],"power-law":[166],"graphs,":[167],"presented.":[169],"accelerator":[171],"demonstrated":[173],"16-nm":[175],"fabricated":[176],"ASIC":[177],"Stratix\u00ae":[179],"10":[180],"FPGA":[181],"platforms.":[182],"Experimental":[183],"results":[184],"show":[185],"more":[186,199],"order":[189],"magnitude":[191,204],"improvement":[192,205],"over":[193,206],"current":[194],"two":[201],"orders":[202],"commercial":[207],"off-the-shelf":[208],"(COTS)":[209],"architectures":[210],"both":[212],"energy":[215],"efficiency.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":11}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}