{"id":"https://openalex.org/W2612094091","doi":"https://doi.org/10.23919/date.2017.7927180","title":"Performance evaluation and optimization of HBM-Enabled GPU for data-intensive applications","display_name":"Performance evaluation and optimization of HBM-Enabled GPU for data-intensive applications","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2612094091","doi":"https://doi.org/10.23919/date.2017.7927180","mag":"2612094091"},"language":"en","primary_location":{"id":"doi:10.23919/date.2017.7927180","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2017.7927180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017","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/A5101831882","display_name":"Maohua Zhu","orcid":"https://orcid.org/0000-0002-8914-9834"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maohua Zhu","raw_affiliation_strings":["University of California, Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051409603","display_name":"Youwei Zhuo","orcid":"https://orcid.org/0000-0002-1557-2613"},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youwei Zhuo","raw_affiliation_strings":["University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011884768","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-9403-5575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"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":"Wenguang Chen","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["University of California, Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101831882"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.2731,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.6232947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9934999942779541,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.991100013256073,"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":0.8882718086242676},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6924649477005005},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5764658451080322},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5645153522491455},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47939467430114746},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.4626100957393646},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45416292548179626},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.437904953956604},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.42238855361938477},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3335076570510864},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3244550824165344},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32059940695762634},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2739778757095337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16813859343528748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882718086242676},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6924649477005005},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5764658451080322},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5645153522491455},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47939467430114746},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.4626100957393646},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45416292548179626},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.437904953956604},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.42238855361938477},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3335076570510864},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3244550824165344},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32059940695762634},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2739778757095337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16813859343528748},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date.2017.7927180","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2017.7927180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133266","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2017&rft.spage=1245&rft.aulast=Zhu&rft.aufirst=Maohua&rft.atitle=Performance+evaluation+and+optimization+of+HBM-Enabled+GPU+for+data-intensive+applications&rft.title=Proceedings+of+the+2017+Design%2C+Automation+and+Test+in+Europe%2C+DATE+2017","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1599149671","https://openalex.org/W1990962327","https://openalex.org/W2055497547","https://openalex.org/W2109473404","https://openalex.org/W2116721352","https://openalex.org/W2127591423","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2618530766","https://openalex.org/W3013652274","https://openalex.org/W6677556258","https://openalex.org/W6683722107","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4376647684","https://openalex.org/W4281677350","https://openalex.org/W4284884988","https://openalex.org/W4214760333","https://openalex.org/W4391042164","https://openalex.org/W2149142646","https://openalex.org/W2250217037","https://openalex.org/W4243474409","https://openalex.org/W2058636218","https://openalex.org/W2993780376"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4],"widely":[5],"used":[6,55],"to":[7,35,120,134,154,170],"accelerate":[8],"data-intensive":[9,16,106],"applications.":[10],"To":[11],"improve":[12,171],"the":[13,57,78,91,122,126,129,137,145,156,160,172,199,206,211],"performance":[14],"of":[15,60,80,128,139,159,174],"applications,":[17,107],"higher":[18,28],"GPU":[19,119,196,202],"memory":[20,42,46,84,175],"bandwidth":[21,29,67,176],"is":[22,85],"desirable.":[23],"Traditional":[24],"GDDR":[25],"memories":[26],"achieve":[27],"by":[30,125],"increasing":[31],"frequency,":[32],"which":[33,62],"leads":[34],"excessive":[36],"power":[37,70],"consumption.":[38],"Recently,":[39],"a":[40,151,189],"new":[41],"technology":[43,52],"called":[44],"high-bandwidth":[45],"(HBM)":[47],"based":[48],"on":[49,116,144,192],"3D":[50],"die-stacking":[51],"has":[53],"been":[54],"in":[56,203],"latest":[58],"generation":[59],"GPUs,":[61],"can":[63],"provide":[64],"both":[65],"high":[66],"and":[68,112,131,205,219],"low":[69],"consumption":[71],"with":[72,198],"in-package":[73],"stacked":[74,83],"DRAM":[75],"memory.":[76],"However,":[77],"capacity":[79,157],"integrated":[81],"in-packaged":[82],"limited":[86],"(e.g.":[87],"only":[88],"4GB":[89],"for":[90,162,177,210,221],"state-of-the-art":[92],"HBM-enabled":[93,118,141],"GPU,":[94],"AMD":[95],"Radeon":[96],"Fury":[97],"X).":[98],"In":[99],"this":[100],"paper,":[101],"we":[102,148],"implement":[103],"two":[104,167,207],"representative":[105],"convolutional":[108],"neural":[109],"network":[110],"(CNN)":[111],"breadth-first":[113],"search":[114],"(BFS)":[115],"an":[117,193],"evaluate":[121],"improvement":[123],"brought":[124],"adoption":[127],"HBM,":[130],"investigate":[132],"techniques":[133,169,209],"fully":[135],"unleash":[136],"benefits":[138],"such":[140],"GPU.":[142],"Based":[143],"evaluation":[146],"results,":[147],"first":[149],"propose":[150],"software":[152],"pipeline":[153],"alleviate":[155],"limitation":[158],"HBM":[161,194],"CNN.":[163],"We":[164],"then":[165],"design":[166],"programming":[168],"utilization":[173],"BFS":[178,212],"application.":[179],"Experiment":[180],"results":[181],"demonstrate":[182],"that":[183],"our":[184],"pipelined":[185],"CNN":[186],"training":[187],"achieves":[188],"1.63x":[190],"speedup":[191],"enabled":[195],"compared":[197],"best":[200],"high-performance":[201],"market,":[204],"optimization":[208],"algorithm":[213],"make":[214],"it":[215],"at":[216],"most":[217],"24.5x(9.8x":[218],"2.5x":[220],"each":[222],"technique,":[223],"respectively)":[224],"faster":[225],"than":[226],"conventional":[227],"implementations.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}