{"id":"https://openalex.org/W2007606233","doi":"https://doi.org/10.1145/1661438.1661440","title":"Sparse Matrix-Vector Multiplication on a Reconfigurable Supercomputer with Application","display_name":"Sparse Matrix-Vector Multiplication on a Reconfigurable Supercomputer with Application","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2007606233","doi":"https://doi.org/10.1145/1661438.1661440","mag":"2007606233"},"language":"en","primary_location":{"id":"doi:10.1145/1661438.1661440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1661438.1661440","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-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/A5104092124","display_name":"David Dubois","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Dubois","raw_affiliation_strings":["Los Alamos National Laboratory","LOS Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"LOS Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110928315","display_name":"Andrew DuBois","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Dubois","raw_affiliation_strings":["Los Alamos National Laboratory","LOS Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"LOS Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067469909","display_name":"Thomas M Boorman","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Boorman","raw_affiliation_strings":["Los Alamos National Laboratory","LOS Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"LOS Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032754570","display_name":"Carolyn Connor","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carolyn Connor","raw_affiliation_strings":["Los Alamos National Laboratory","LOS Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"LOS Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050561633","display_name":"Steve Poole","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Poole","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0612,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86252542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8465917110443115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6677737832069397},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6412861347198486},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5945344567298889},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5929837822914124},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5866585969924927},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5188649892807007},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4805082082748413},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4554824233055115},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.4532212018966675},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4101318120956421},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.332886666059494},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2892720699310303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2497881054878235},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.19699272513389587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465917110443115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6677737832069397},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6412861347198486},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5945344567298889},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5929837822914124},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5866585969924927},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5188649892807007},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4805082082748413},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4554824233055115},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.4532212018966675},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4101318120956421},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.332886666059494},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2892720699310303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2497881054878235},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.19699272513389587},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1661438.1661440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1661438.1661440","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W245914994","https://openalex.org/W1575701986","https://openalex.org/W1581309603","https://openalex.org/W1965537434","https://openalex.org/W1981252059","https://openalex.org/W1987393840","https://openalex.org/W2092608522","https://openalex.org/W2098513105","https://openalex.org/W2098841537","https://openalex.org/W2115002670","https://openalex.org/W2119697285","https://openalex.org/W2146369740","https://openalex.org/W2149328392","https://openalex.org/W2152567198","https://openalex.org/W2161761794","https://openalex.org/W2725179571","https://openalex.org/W4230252700","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3215589575","https://openalex.org/W2336476964","https://openalex.org/W3150959508","https://openalex.org/W1571090276","https://openalex.org/W3150370983","https://openalex.org/W2773283032","https://openalex.org/W2239119680","https://openalex.org/W2012407419","https://openalex.org/W4297795876","https://openalex.org/W4302004660"],"abstract_inverted_index":{"Double":[0],"precision":[1],"floating":[2,161],"point":[3,162],"Sparse":[4],"Matrix-Vector":[5],"Multiplication":[6],"(SMVM)":[7],"is":[8],"a":[9,54,121,184,201],"critical":[10],"computational":[11],"kernel":[12],"used":[13],"in":[14,41],"iterative":[15],"solvers":[16],"for":[17],"systems":[18],"of":[19,38,75,98,106,128,143,155,173,192],"sparse":[20,29],"linear":[21],"equations.":[22],"The":[23,83,126],"poor":[24,42],"data":[25],"locality":[26],"exhibited":[27],"by":[28],"matrices":[30],"along":[31],"with":[32,57,101,117],"the":[33,76,87,92,96,102,107,113,118,141,144,152,156,166,171,177,193,197,209],"high":[34],"memory":[35,62,179],"bandwidth":[36,105,158,180],"requirements":[37],"SMVM":[39,77,211],"result":[40],"performance":[43,89,116],"on":[44,78],"general":[45],"purpose":[46],"processors.":[47],"Field":[48],"Programmable":[49],"Gate":[50],"Arrays":[51],"(FPGAs)":[52],"offer":[53],"possible":[55],"alternative":[56],"their":[58],"customizable":[59],"and":[60,64,130,146],"application-targeted":[61],"sub-system":[63],"processing":[65],"elements.":[66],"In":[67],"this":[68],"work":[69],"we":[70,199],"investigate":[71],"two":[72],"separate":[73],"implementations":[74,111],"an":[79],"SRC-6":[80],"MAPStation":[81],"workstation.":[82],"first":[84],"implementation":[85,94],"investigates":[86],"peak":[88,160],"capability,":[90],"while":[91],"second":[93,119,210],"balances":[95],"amount":[97,172],"instantiated":[99],"logic":[100,175],"available":[103,157,178],"sustained":[104,115],"FPGA":[108,145],"subsystem.":[109],"Both":[110],"yield":[112],"same":[114],"producing":[120],"much":[122,185],"more":[123,186],"efficient":[124,187],"solution.":[125,188],"metrics":[127],"processor":[129],"application":[131],"balance":[132,170],"are":[133],"introduced":[134],"to":[135,159,165,169,176],"help":[136],"provide":[137,183],"some":[138],"insight":[139],"into":[140],"efficiencies":[142],"CPU":[147],"based":[148],"solutions":[149],"explicitly":[150],"showing":[151],"tight":[153],"coupling":[154],"performance.":[163],"Due":[164],"FPGAs":[167],"ability":[168],"implemented":[174,203],"it":[181],"can":[182],"Finally,":[189],"making":[190],"use":[191],"lessons":[194],"learned":[195],"implementing":[196],"SMVM,":[198],"present":[200],"fully":[202],"non-preconditioned":[204],"Conjugate":[205],"Gradient":[206],"Algorithm":[207],"utilizing":[208],"design.":[212]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
