{"id":"https://openalex.org/W3011253470","doi":"https://doi.org/10.1145/3381427.3381428","title":"Sparse Matrix-Dense Matrix Multiplication on Heterogeneous CPU+FPGA Embedded System","display_name":"Sparse Matrix-Dense Matrix Multiplication on Heterogeneous CPU+FPGA Embedded System","publication_year":2020,"publication_date":"2020-01-21","ids":{"openalex":"https://openalex.org/W3011253470","doi":"https://doi.org/10.1145/3381427.3381428","mag":"3011253470"},"language":"en","primary_location":{"id":"doi:10.1145/3381427.3381428","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3381427.3381428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures / 9th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms","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/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":true,"raw_author_name":"Mohammad Hosseinabady","raw_affiliation_strings":["University of Bristol, Bristol"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol","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 Nunez-Yanez","raw_affiliation_strings":["University of Bristol, Bristol"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000075032"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":1.1552,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75479094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9901000261306763,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7718080282211304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634454965591431},{"id":"https://openalex.org/keywords/mpsoc","display_name":"MPSoC","score":0.7070369720458984},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6345764994621277},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.629270613193512},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5300336480140686},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4753698706626892},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45930182933807373},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4446059763431549},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3997590243816376},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3983602821826935},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.30601930618286133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23701393604278564}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7718080282211304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634454965591431},{"id":"https://openalex.org/C2777187653","wikidata":"https://www.wikidata.org/wiki/Q975106","display_name":"MPSoC","level":3,"score":0.7070369720458984},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6345764994621277},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.629270613193512},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5300336480140686},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4753698706626892},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45930182933807373},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4446059763431549},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3997590243816376},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3983602821826935},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.30601930618286133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23701393604278564},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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:10.1145/3381427.3381428","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3381427.3381428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures / 9th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2004455575","https://openalex.org/W2092013581","https://openalex.org/W2128131218","https://openalex.org/W2128853364","https://openalex.org/W2279098554","https://openalex.org/W2626052469","https://openalex.org/W2727717548","https://openalex.org/W2941763154","https://openalex.org/W2949619037","https://openalex.org/W2968028996","https://openalex.org/W4243261006","https://openalex.org/W4244330903"],"related_works":["https://openalex.org/W1976012348","https://openalex.org/W2614713859","https://openalex.org/W2002682434","https://openalex.org/W4387782849","https://openalex.org/W2137671689","https://openalex.org/W2113449380","https://openalex.org/W2012131147","https://openalex.org/W3146394219","https://openalex.org/W2157008728","https://openalex.org/W2016942572"],"abstract_inverted_index":{"Embedded":[0],"intelligence":[1],"is":[2,88],"becoming":[3],"the":[4,32,72,85,95,112,125,141,148,159,172],"primary":[5],"driver":[6],"for":[7],"new":[8],"applications":[9,24],"in":[10,79,105,123,128],"industry,":[11],"healthcare,":[12],"and":[13,38,58,102],"automotive,":[14],"to":[15,68,83,110,166],"name":[16],"a":[17,65,89,99,106,152,162],"few.":[18],"The":[19],"main":[20],"characteristics":[21],"of":[22,71,98,114,144,164],"these":[23,44,76],"are":[25],"high":[26],"computational":[27],"demand,":[28],"real-time":[29],"interaction":[30],"with":[31,169],"environment,":[33],"security,":[34],"low":[35],"power":[36],"consumption,":[37],"local":[39],"autonomy,":[40],"among":[41],"others.":[42],"Addressing":[43],"diverse":[45],"characteristics,":[46,74],"researchers":[47],"have":[48,119],"proposed":[49],"heterogeneous":[50,107,153],"multicore":[51,100],"embedded":[52,108,155],"systems":[53],"comprising":[54],"CPUs,":[55],"GPUs,":[56],"FPGAs,":[57],"ASICs.":[59],"Whereas":[60],"each":[61],"computing":[62],"element":[63],"provides":[64],"unique":[66],"capability":[67],"enable":[69],"one":[70],"application":[73,82],"collaborating":[75],"processing":[77],"cores":[78],"running":[80],"an":[81,103,175],"get":[84],"maximum":[86],"performance":[87,113,160],"crucial":[90],"challenge.":[91],"This":[92],"paper":[93],"considers":[94],"collaborative":[96,142],"usage":[97],"CPU":[101],"FPGA":[104,173],"system":[109],"improve":[111,158],"sparse":[115],"matrix":[116],"operations,":[117],"which":[118],"been":[120],"essential":[121],"techniques":[122],"reducing":[124],"inference":[126],"complexity":[127],"machine":[129],"learning":[130],"techniques,":[131],"especially":[132],"deep":[133],"convolutional":[134],"neural":[135],"networks.":[136],"Experimental":[137],"results":[138],"show":[139],"that":[140],"execution":[143],"sparse-matrix-dense-matrix":[145],"multiplication":[146],"on":[147],"Xilinx":[149],"Zynq":[150],"MPSoC,":[151],"CPU+FPGA":[154],"system,":[156],"can":[157],"by":[161],"factor":[163],"up":[165],"42%":[167],"compared":[168],"just":[170],"using":[171],"as":[174],"accelerator.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}