{"id":"https://openalex.org/W2284370437","doi":"https://doi.org/10.1109/igcc.2015.7393735","title":"Energy efficient multi-level tiling for dense matrix multiplication on many-core architecture","display_name":"Energy efficient multi-level tiling for dense matrix multiplication on many-core architecture","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2284370437","doi":"https://doi.org/10.1109/igcc.2015.7393735","mag":"2284370437"},"language":"en","primary_location":{"id":"doi:10.1109/igcc.2015.7393735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2015.7393735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Sixth International Green and Sustainable Computing Conference (IGSC)","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/A5101689401","display_name":"Haitao Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haitao Wei","raw_affiliation_strings":["CAPSL University of Delaware Newark, DE"],"affiliations":[{"raw_affiliation_string":"CAPSL University of Delaware Newark, DE","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046024163","display_name":"Guang R. Gao","orcid":"https://orcid.org/0000-0002-5265-7528"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guang R. Gao","raw_affiliation_strings":["CAPSL University of Delaware Newark, DE"],"affiliations":[{"raw_affiliation_string":"CAPSL University of Delaware Newark, DE","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103360010","display_name":"Elkin Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125489","display_name":"Synaptics (United States)","ror":"https://ror.org/031tq8403","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elkin Garcia","raw_affiliation_strings":["Synaptics Inc. San Jose, CA"],"affiliations":[{"raw_affiliation_string":"Synaptics Inc. San Jose, CA","institution_ids":["https://openalex.org/I4210125489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101689401"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14238082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440071702003479},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.6558870077133179},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6316497921943665},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5586698651313782},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5479793548583984},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4991598129272461},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4403623342514038},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4276544153690338},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4141383171081543},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4100942015647888},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4074980318546295},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35041338205337524},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33316776156425476},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11112663149833679},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10865962505340576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09917804598808289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440071702003479},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.6558870077133179},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6316497921943665},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5586698651313782},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5479793548583984},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4991598129272461},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4403623342514038},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4276544153690338},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4141383171081543},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4100942015647888},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4074980318546295},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35041338205337524},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33316776156425476},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11112663149833679},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10865962505340576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09917804598808289},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igcc.2015.7393735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2015.7393735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Sixth International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1859126261","https://openalex.org/W1981259316","https://openalex.org/W2006312753","https://openalex.org/W2034761517","https://openalex.org/W2038897871","https://openalex.org/W2042297499","https://openalex.org/W2055534506","https://openalex.org/W2090942242","https://openalex.org/W2093736609","https://openalex.org/W2098220211","https://openalex.org/W2098335003","https://openalex.org/W2105524676","https://openalex.org/W2158158791","https://openalex.org/W4244580719","https://openalex.org/W4253068647","https://openalex.org/W4255560897","https://openalex.org/W6645621993","https://openalex.org/W6651700774","https://openalex.org/W6661150328"],"related_works":["https://openalex.org/W4392590355","https://openalex.org/W3151633427","https://openalex.org/W2212894501","https://openalex.org/W2793465010","https://openalex.org/W3024050170","https://openalex.org/W2109451123","https://openalex.org/W4378977321","https://openalex.org/W1976168335","https://openalex.org/W3211992815","https://openalex.org/W2099571870"],"abstract_inverted_index":{"With":[0],"computing":[1],"systems":[2],"marching":[3],"to":[4,45,84,91,123],"exascale":[5],"and":[6,15,37,87,97,126],"big":[7],"data":[8],"era,":[9],"power":[10],"consumption":[11],"has":[12,38],"become":[13],"more":[14,16],"important":[17],"for":[18,59,106],"the":[19,28,32,42,77,99],"system":[20,34],"design.":[21,48],"Energy":[22],"efficiency":[23],"is":[24],"becoming":[25],"one":[26,94],"of":[27,103],"critical":[29],"dimensions":[30],"in":[31],"computer":[33],"design":[35],"space":[36],"been":[39],"considered":[40],"from":[41,81,88],"hardware":[43],"architecture":[44,65],"software":[46],"algorithm":[47],"In":[49],"this":[50],"paper,":[51],"we":[52,75],"proposed":[53],"an":[54],"energy":[55,73,107,118],"efficient":[56],"multi-level":[57],"tiling":[58,80,101,116],"dense":[60],"matrix":[61],"multiplication":[62],"on":[63,71],"many-core":[64],"with":[66],"software-managed":[67],"memory":[68,83],"hierarchy.":[69],"Based":[70],"our":[72,114],"model,":[74],"integrated":[76],"two":[78],"level":[79,105],"off-chip":[82],"on-chip":[85,89],"SRAM":[86,90],"register":[92],"into":[93],"unified":[95],"formulation":[96],"obtained":[98],"optimal":[100,115],"sizes":[102],"each":[104],"efficiency.":[108],"The":[109],"experimental":[110],"results":[111],"showed":[112],"that":[113],"improved":[117],"cost":[119],"by":[120],"17.9%":[121],"compared":[122],"non-optimal":[124],"solution":[125],"achieved":[127],"87.5%":[128],"perk":[129],"performance.":[130]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}