{"id":"https://openalex.org/W2148570406","doi":"https://doi.org/10.1109/sasp.2010.5521144","title":"FPGA and GPU implementation of large scale SpMV","display_name":"FPGA and GPU implementation of large scale SpMV","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2148570406","doi":"https://doi.org/10.1109/sasp.2010.5521144","mag":"2148570406"},"language":"en","primary_location":{"id":"doi:10.1109/sasp.2010.5521144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2010.5521144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 8th Symposium on Application Specific Processors (SASP)","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/A5009175141","display_name":"Yi Shan","orcid":"https://orcid.org/0000-0003-2646-8835"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Shan","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056404134","display_name":"Tianji Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianji Wu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408076","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-2918-1912"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384118","display_name":"Zilong Wang","orcid":"https://orcid.org/0009-0000-4026-0104"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Wang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100833305","display_name":"Ningyi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningyi Xu","raw_affiliation_strings":["Hardware Computing Group, Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Hardware Computing Group, Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103867707","display_name":"Huazhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5009175141"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.849,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91412616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and 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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and 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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9927999973297119,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9927999973297119,"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":0.8785637617111206},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7236198782920837},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6572707891464233},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6294329762458801},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6267334222793579},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6200001239776611},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.426751971244812},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.42512571811676025},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3503933846950531},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2412230670452118},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.163068950176239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8785637617111206},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7236198782920837},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6572707891464233},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6294329762458801},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6267334222793579},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6200001239776611},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.426751971244812},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.42512571811676025},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3503933846950531},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2412230670452118},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.163068950176239},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sasp.2010.5521144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2010.5521144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 8th Symposium on Application Specific Processors (SASP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1487278226","https://openalex.org/W1854214752","https://openalex.org/W1982565841","https://openalex.org/W2035080386","https://openalex.org/W2080804082","https://openalex.org/W2103877122","https://openalex.org/W2108540054","https://openalex.org/W2122862680","https://openalex.org/W2124007994","https://openalex.org/W2128131218","https://openalex.org/W2152567198","https://openalex.org/W2183317050","https://openalex.org/W4285719527","https://openalex.org/W4316084067","https://openalex.org/W6629175729","https://openalex.org/W6686667855"],"related_works":["https://openalex.org/W2143593481","https://openalex.org/W3179800311","https://openalex.org/W2370911386","https://openalex.org/W2130342641","https://openalex.org/W2502696069","https://openalex.org/W108745714","https://openalex.org/W4319586056","https://openalex.org/W2289758917","https://openalex.org/W3091969046","https://openalex.org/W3093098265"],"abstract_inverted_index":{"Sparse":[0,101],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4],"a":[5,88,98,118,130],"fundamental":[6],"operation":[7],"for":[8],"many":[9],"applications.":[10],"Many":[11],"studies":[12],"have":[13],"been":[14],"done":[15],"to":[16,72],"implement":[17],"the":[18,28,40,52,60,65,73,83],"SpMV":[19,46,92],"on":[20,27,117],"different":[21],"platforms,":[22],"while":[23],"few":[24],"work":[25],"focused":[26],"very":[29],"large":[30,44],"scale":[31,45,77],"datasets":[32,76],"with":[33,47,94,129],"millions":[34],"of":[35,42,54,75],"dimensions.":[36],"This":[37],"paper":[38],"addresses":[39],"challenges":[41],"implementing":[43],"FPGA":[48,61,107,121],"and":[49,68,78,90,108,114,122],"GPU":[50,84,109],"in":[51],"application":[53],"web":[55],"link":[56],"graph":[57],"analysis.":[58],"In":[59,82],"implementation,":[62,85],"we":[63,86],"designed":[64,87],"task":[66],"partition":[67],"memory":[69],"hierarchy":[70],"according":[71],"analysis":[74],"their":[79],"access":[80],"pattern.":[81],"fast":[89],"scalable":[91],"routine":[93],"three":[95],"passes,":[96],"using":[97],"modified":[99],"Compressed":[100],"Row":[102],"format.":[103],"Results":[104],"show":[105],"that":[106],"implementation":[110],"achieves":[111],"about":[112],"29x":[113],"30x":[115],"speedup":[116],"StratixII":[119],"EP2S180":[120],"Radeon":[123],"5870":[124],"Graphic":[125],"Card":[126],"respectively":[127],"compared":[128],"Phenom":[131],"9550":[132],"CPU.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}