{"id":"https://openalex.org/W2093383161","doi":"https://doi.org/10.1155/2014/712085","title":"A Low-Power Scalable Stream Compute Accelerator for General Matrix Multiply (GEMM)","display_name":"A Low-Power Scalable Stream Compute Accelerator for General Matrix Multiply (GEMM)","publication_year":2014,"publication_date":"2014-02-24","ids":{"openalex":"https://openalex.org/W2093383161","doi":"https://doi.org/10.1155/2014/712085","mag":"2093383161"},"language":"en","primary_location":{"id":"doi:10.1155/2014/712085","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2014/712085","pdf_url":"https://downloads.hindawi.com/archive/2014/712085.pdf","source":{"id":"https://openalex.org/S81291924","display_name":"VLSI design","issn_l":"1026-7123","issn":["1026-7123","1065-514X","1563-5171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"VLSI Design","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/archive/2014/712085.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066673825","display_name":"Antony Savich","orcid":"https://orcid.org/0000-0002-7589-477X"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Antony Savich","raw_affiliation_strings":["School of Engineering, University of Guelph, Guelph, ON, Canada N1G 2W1"],"affiliations":[{"raw_affiliation_string":"School of Engineering, University of Guelph, Guelph, ON, Canada N1G 2W1","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011873620","display_name":"Shawki Areibi","orcid":"https://orcid.org/0000-0003-4832-0911"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shawki Areibi","raw_affiliation_strings":["School of Engineering, University of Guelph, Guelph, ON, Canada N1G 2W1"],"affiliations":[{"raw_affiliation_string":"School of Engineering, University of Guelph, Guelph, ON, Canada N1G 2W1","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066673825"],"corresponding_institution_ids":["https://openalex.org/I79817857"],"apc_list":null,"apc_paid":null,"fwci":0.3164,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62172156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2014","issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976999759674072,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767771303653717},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7629531025886536},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6613901853561401},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6289032101631165},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6276534795761108},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5304951667785645},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5050366520881653},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.503675639629364},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.48828721046447754},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.45614832639694214},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43780988454818726},{"id":"https://openalex.org/keywords/power-budget","display_name":"Power budget","score":0.42718225717544556},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4107235074043274},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38091886043548584},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3721936345100403},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35217827558517456},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18359604477882385},{"id":"https://openalex.org/keywords/electric-power-system","display_name":"Electric power system","score":0.1591835916042328},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14193257689476013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767771303653717},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7629531025886536},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6613901853561401},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6289032101631165},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6276534795761108},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5304951667785645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5050366520881653},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.503675639629364},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.48828721046447754},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.45614832639694214},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43780988454818726},{"id":"https://openalex.org/C149768029","wikidata":"https://www.wikidata.org/wiki/Q1509342","display_name":"Power budget","level":4,"score":0.42718225717544556},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4107235074043274},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38091886043548584},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3721936345100403},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35217827558517456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18359604477882385},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.1591835916042328},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14193257689476013},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1155/2014/712085","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2014/712085","pdf_url":"https://downloads.hindawi.com/archive/2014/712085.pdf","source":{"id":"https://openalex.org/S81291924","display_name":"VLSI design","issn_l":"1026-7123","issn":["1026-7123","1065-514X","1563-5171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"VLSI Design","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1155/2014/712085","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2014/712085","pdf_url":"https://downloads.hindawi.com/archive/2014/712085.pdf","source":{"id":"https://openalex.org/S81291924","display_name":"VLSI design","issn_l":"1026-7123","issn":["1026-7123","1065-514X","1563-5171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"VLSI Design","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2093383161.pdf","grobid_xml":"https://content.openalex.org/works/W2093383161.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1511216606","https://openalex.org/W1981550505","https://openalex.org/W1995812446","https://openalex.org/W2064712527","https://openalex.org/W2119560898","https://openalex.org/W2133757342","https://openalex.org/W2143757465","https://openalex.org/W2148004019","https://openalex.org/W2165354374","https://openalex.org/W2333043602","https://openalex.org/W4249774071"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2739740241","https://openalex.org/W2475524688","https://openalex.org/W2085105049","https://openalex.org/W2526069705","https://openalex.org/W2148563915","https://openalex.org/W2019153376","https://openalex.org/W2024016913","https://openalex.org/W2981664121","https://openalex.org/W2796552083"],"abstract_inverted_index":{"Many":[0],"applications":[1,61],"ranging":[2],"from":[3],"machine":[4,9],"learning,":[5],"image":[6],"processing,":[7],"and":[8,71,101,120],"vision":[10],"to":[11,48,94],"optimization":[12],"utilize":[13],"matrix":[14],"multiplication":[15],"as":[16,106],"a":[17,36,49,77,107],"fundamental":[18],"block.":[19],"Matrix":[20],"operations":[21],"play":[22],"an":[23],"important":[24,114],"role":[25],"in":[26,59],"determining":[27],"the":[28],"performance":[29,47,67,123],"of":[30,45,91,98],"such":[31],"applications.":[32],"This":[33],"paper":[34],"proposes":[35],"novel":[37],"efficient,":[38],"highly":[39],"scalable":[40],"hardware":[41,82],"accelerator":[42,83],"that":[43],"is":[44,84,102,124],"equivalent":[46,111],"2":[50],"GHz":[51],"quad":[52],"core":[53],"PC":[54],"but":[55],"can":[56],"be":[57],"used":[58],"low-power":[60],"targeting":[62],"embedded":[63],"systems":[64],"requiring":[65],"high":[66],"computation.":[68],"Power,":[69],"performance,":[70],"resource":[72],"consumption":[73],"are":[74],"demonstrated":[75],"on":[76],"fully-functional":[78],"prototype.":[79],"The":[80],"proposed":[81],"36\u00d7":[85],"more":[86,104],"energy":[87],"efficient":[88,105],"per":[89],"unit":[90],"computation":[92],"compared":[93],"state-of-the-art":[95],"Xeon":[96],"processor":[97],"equal":[99],"vintage":[100],"14\u00d7":[103],"stand-alone":[108],"platform":[109],"with":[110],"performance.":[112],"An":[113],"comparison":[115],"between":[116],"simulated":[117],"system":[118,122],"estimates":[119],"real":[121],"carried":[125],"out.":[126]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}