{"id":"https://openalex.org/W2791186466","doi":"https://doi.org/10.1109/tvlsi.2018.2791442","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":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2791186466","doi":"https://doi.org/10.1109/tvlsi.2018.2791442","mag":"2791186466"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2018.2791442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2018.2791442","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-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 at Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","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/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, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["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, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","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 at Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","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":1.6714,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.88240343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":"5","first_page":"831","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9908000230789185,"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/computer-science","display_name":"Computer science","score":0.8704591393470764},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6734625101089478},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6243619918823242},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5512307286262512},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.49700358510017395},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46271345019340515},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4279060661792755},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41531819105148315},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3352137804031372},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33075782656669617},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3225126564502716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15895992517471313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704591393470764},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6734625101089478},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6243619918823242},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5512307286262512},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.49700358510017395},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46271345019340515},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4279060661792755},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41531819105148315},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3352137804031372},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33075782656669617},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3225126564502716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15895992517471313},{"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:10.1109/tvlsi.2018.2791442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2018.2791442","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133225","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-133225","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":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3069263526","display_name":null,"funder_award_id":"1719160","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5768095042","display_name":null,"funder_award_id":"1500848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G801074273","display_name":null,"funder_award_id":"1533933","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1557692423","https://openalex.org/W1599149671","https://openalex.org/W1686810756","https://openalex.org/W1990962327","https://openalex.org/W2042545849","https://openalex.org/W2055497547","https://openalex.org/W2094756095","https://openalex.org/W2109473404","https://openalex.org/W2116721352","https://openalex.org/W2119144962","https://openalex.org/W2127591423","https://openalex.org/W2131413854","https://openalex.org/W2133156997","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2406293284","https://openalex.org/W2489529491","https://openalex.org/W2950094539","https://openalex.org/W2964174152","https://openalex.org/W2964299589","https://openalex.org/W3013652274","https://openalex.org/W3139689176","https://openalex.org/W4237819810","https://openalex.org/W4256629673","https://openalex.org/W6677556258","https://openalex.org/W6683722107","https://openalex.org/W6684191040","https://openalex.org/W6713184358"],"related_works":["https://openalex.org/W4376647684","https://openalex.org/W4221139464","https://openalex.org/W2141978748","https://openalex.org/W4243474409","https://openalex.org/W2993780376","https://openalex.org/W3145767355","https://openalex.org/W2607256436","https://openalex.org/W2114927422","https://openalex.org/W2528745529","https://openalex.org/W1966777863"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"are":[4],"widely":[5],"used":[6,58],"to":[7,38,122,134,137,157,173],"accelerate":[8],"data-intensive":[9,16,108],"applications.":[10],"To":[11],"improve":[12,174],"the":[13,60,80,93,124,128,131,140,148,159,163,175,202,209,214],"performance":[14],"of":[15,63,82,130,142,162,177],"applications,":[17,109],"higher":[18,31],"GPU":[19,121,199,205],"memory":[20,45,49,85,178],"bandwidth":[21,32,70,179],"is":[22,86],"desirable.":[23],"Traditional":[24],"graphics":[25],"double":[26],"data":[27],"rate":[28],"memories":[29],"achieve":[30],"by":[33,127],"increasing":[34],"frequency,":[35],"which":[36,65],"leads":[37],"excessive":[39],"power":[40,73],"consumption.":[41],"Recently,":[42],"a":[43,154,192],"new":[44],"technology":[46,55],"called":[47],"high-bandwidth":[48],"(HBM)":[50],"based":[51],"on":[52,118,147,196],"3-D":[53],"die-stacking":[54],"has":[56],"been":[57],"in":[59,206],"latest":[61],"generation":[62],"GPUs,":[64],"can":[66],"provide":[67],"both":[68],"high":[69],"and":[71,114,133,208,223],"low":[72],"consumption":[74],"with":[75,201],"in-package-stacked":[76,84],"DRAM":[77],"memory.":[78],"However,":[79],"capacity":[81,160],"integrated":[83],"limited":[87],"(e.g.,":[88],"only":[89],"4":[90],"GB":[91],"for":[92,165,180,213,225],"state-of-the-art":[94],"HBM-enabled":[95,120,144,198],"GPU,":[96],"AMD":[97],"Radeon":[98],"Fury":[99],"X).":[100],"In":[101],"this":[102],"paper,":[103],"we":[104,151],"implement":[105],"two":[106,170,210],"representative":[107],"convolutional":[110],"neural":[111],"network":[112],"(CNN)":[113],"breadth-first":[115],"search":[116],"(BFS)":[117],"an":[119,197],"evaluate":[123],"improvement":[125],"brought":[126],"adoption":[129],"HBM,":[132],"investigate":[135],"techniques":[136,172,212],"fully":[138],"unleash":[139],"benefits":[141],"such":[143],"GPU.":[145],"Based":[146],"evaluation":[149],"results,":[150],"first":[152],"propose":[153],"software":[155],"pipeline":[156],"alleviate":[158],"limitation":[161],"HBM":[164],"CNN.":[166],"We":[167],"then":[168],"design":[169],"programming":[171],"utilization":[176],"BFS":[181,215],"application.":[182],"Experimental":[183],"results":[184],"demonstrate":[185],"that":[186],"our":[187],"pipelined":[188],"CNN":[189],"training":[190],"achieves":[191],"1.63":[193],"\u00d7":[194],"speedup":[195],"compared":[200],"best":[203],"high-performance":[204],"market,":[207],"optimization":[211],"algorithm":[216],"make":[217],"it":[218],"at":[219],"most":[220],"24.5\u00d7":[221],"(9.8\u00d7":[222],"2.5\u00d7":[224],"each":[226],"technique,":[227],"respectively)":[228],"faster":[229],"than":[230],"conventional":[231],"implementations.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}