{"id":"https://openalex.org/W2941763154","doi":"https://doi.org/10.1109/tcad.2019.2912923","title":"A Streaming Dataflow Engine for Sparse Matrix-Vector Multiplication Using High-Level Synthesis","display_name":"A Streaming Dataflow Engine for Sparse Matrix-Vector Multiplication Using High-Level Synthesis","publication_year":2019,"publication_date":"2019-04-25","ids":{"openalex":"https://openalex.org/W2941763154","doi":"https://doi.org/10.1109/tcad.2019.2912923","mag":"2941763154"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2019.2912923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2019.2912923","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research-information.bris.ac.uk/en/publications/648aa45c-3dad-4170-b872-e55496f4f999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000075032","display_name":"Mohammad Hosseinabady","orcid":"https://orcid.org/0000-0003-3989-4999"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohammad Hosseinabady","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"],"raw_orcid":"https://orcid.org/0000-0003-3989-4999","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005255540","display_name":"Jose Nunez\u2010Yanez","orcid":"https://orcid.org/0000-0002-5153-5481"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose Luis Nunez-Yanez","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5153-5481","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":3.7545,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93350873,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"6","first_page":"1272","last_page":"1285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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/T10904","display_name":"Embedded Systems Design 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/dataflow","display_name":"Dataflow","score":0.8613941073417664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8273335099220276},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6763038635253906},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6623241901397705},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5187814235687256},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5022194385528564},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4987063407897949},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4746827781200409},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2532159686088562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07302945852279663}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8613941073417664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273335099220276},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6763038635253906},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6623241901397705},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5187814235687256},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5022194385528564},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4987063407897949},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4746827781200409},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2532159686088562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07302945852279663},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcad.2019.2912923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2019.2912923","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/648aa45c-3dad-4170-b872-e55496f4f999","is_oa":true,"landing_page_url":null,"pdf_url":"https://research-information.bris.ac.uk/en/publications/648aa45c-3dad-4170-b872-e55496f4f999","source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:research-information.bris.ac.uk:publications/648aa45c-3dad-4170-b872-e55496f4f999","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/648aa45c-3dad-4170-b872-e55496f4f999","pdf_url":"https://research-information.bris.ac.uk/en/publications/648aa45c-3dad-4170-b872-e55496f4f999","source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hosseinabady, M & Nunez-Yanez, J 2019, 'A Streaming Dataflow Engine for Sparse Matrix-Vector Multiplication using High-Level Synthesis', IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. https://doi.org/10.1109/TCAD.2019.2912923","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:research-information.bris.ac.uk:publications/648aa45c-3dad-4170-b872-e55496f4f999","is_oa":true,"landing_page_url":null,"pdf_url":"https://research-information.bris.ac.uk/en/publications/648aa45c-3dad-4170-b872-e55496f4f999","source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G2722607983","display_name":null,"funder_award_id":"EP/N002539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2921531490","display_name":"ENergy Efficient Adaptive Computing with multi-grain heterogeneous architectures (ENEAC)","funder_award_id":"EP/N002539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2941763154.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W101663867","https://openalex.org/W138322339","https://openalex.org/W1969102784","https://openalex.org/W1981252059","https://openalex.org/W1994515555","https://openalex.org/W1998336350","https://openalex.org/W2007441708","https://openalex.org/W2035080386","https://openalex.org/W2081874478","https://openalex.org/W2103660617","https://openalex.org/W2108540054","https://openalex.org/W2112678088","https://openalex.org/W2124408528","https://openalex.org/W2128853364","https://openalex.org/W2153635508","https://openalex.org/W2343695530","https://openalex.org/W2530417694","https://openalex.org/W2535419693","https://openalex.org/W2565125333","https://openalex.org/W2594491068","https://openalex.org/W2626052469","https://openalex.org/W2763664021","https://openalex.org/W2766681651","https://openalex.org/W2801866268","https://openalex.org/W3102169921","https://openalex.org/W4232624858","https://openalex.org/W4245683599","https://openalex.org/W6605724384","https://openalex.org/W6751141275"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4318347836","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Using":[0],"high-level":[1],"synthesis":[2],"techniques,":[3],"this":[4,31,60],"paper":[5,61],"proposes":[6],"an":[7,110,126,147,216,226],"adaptable":[8],"high-performance":[9],"streaming":[10,44],"dataflow":[11,40],"engine":[12,32],"for":[13,21,71,104,121,140],"sparse":[14],"matrix":[15],"dense":[16],"vector":[17,173],"multiplication":[18],"(SpMV)":[19],"suitable":[20],"embedded":[22,102,117,155,202],"FPGAs.":[23],"As":[24],"the":[25,34,49,54,77,93,116,133,141,154,165,171,179,184,189,193,201,211,233],"SpMV":[26,167,196],"is":[27,62,119,136,213],"a":[28],"memory-bound":[29,72],"algorithm,":[30,176],"combines":[33],"three":[35],"concepts":[36],"of":[37,48,59,76,101,113,129,143,150,178,191,200,219,229],"loop":[38],"pipelining,":[39],"graph,":[41],"and":[42,80,106,157,204,221],"data":[43],"to":[45,53,63,74,99,153,169,198,232],"utilize":[46],"most":[47],"memory":[50],"bandwidth":[51],"available":[52],"FPGA.":[55],"The":[56,88,206],"main":[57],"goal":[58],"show":[64,209],"that":[65,75,92,100,199,210],"FPGAs":[66],"can":[67],"provide":[68],"comparable":[69],"performance":[70,97],"applications":[73],"corresponding":[78],"CPUs":[79],"GPUs":[81,103],"but":[82],"with":[83],"significantly":[84],"less":[85,223],"energy":[86,138,224],"consumption.":[87],"experimental":[89,207],"results":[90,208],"indicate":[91],"FPGA":[94,134,212],"provides":[95],"higher":[96],"compared":[98,152,197,231],"small":[105],"medium-size":[107],"matrices":[108,124,145],"by":[109,125,146,215,225],"average":[111,127,148,217,227],"factor":[112,128,149,218,228],"3.25":[114],"whereas":[115],"GPU":[118],"faster":[120,214],"larger":[122],"size":[123],"1.58.":[130],"In":[131],"addition,":[132],"implementation":[135],"more":[137],"efficient":[139],"range":[142],"considered":[144],"8.9":[151],"CPU":[156,203],"GPU.":[158,205,234],"A":[159],"case":[160],"study":[161],"based":[162],"on":[163],"adapting":[164],"proposed":[166,194],"optimization":[168],"accelerate":[170],"support":[172],"machine":[174,185],"(SVM)":[175],"one":[177],"successful":[180],"classification":[181],"techniques":[182],"in":[183],"learning":[186],"literature,":[187],"justifies":[188],"benefits":[190],"utilizing":[192],"FPGA-based":[195],"1.7":[220],"consumes":[222],"6.8":[230]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}