{"id":"https://openalex.org/W4360831834","doi":"https://doi.org/10.1109/hpca56546.2023.10070941","title":"High Performance and Power Efficient Accelerator for Cloud Inference","display_name":"High Performance and Power Efficient Accelerator for Cloud Inference","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831834","doi":"https://doi.org/10.1109/hpca56546.2023.10070941"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10070941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10070941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","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/A5100567886","display_name":"Jianguo Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianguo Yao","raw_affiliation_strings":["SJTU and Enflame-Tech Inc.,Shanghai,China","SJTU and Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SJTU and Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"SJTU and Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397092","display_name":"Hao Zhou","orcid":"https://orcid.org/0009-0009-3536-7623"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619354","display_name":"Yalin Zhang","orcid":"https://orcid.org/0000-0002-3244-1084"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalin Zhang","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414383","display_name":"Ying Li","orcid":"https://orcid.org/0000-0003-0608-9619"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101541920","display_name":"Chuang Feng","orcid":"https://orcid.org/0000-0003-4442-5345"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Feng","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362202","display_name":"Shi Chen","orcid":"https://orcid.org/0000-0002-3749-4767"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Chen","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085691361","display_name":"Jiaoyan Chen","orcid":"https://orcid.org/0000-0003-4643-6750"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaoyan Chen","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595665","display_name":"Yongdong Wang","orcid":"https://orcid.org/0000-0002-9033-827X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Wang","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034824668","display_name":"Qiaojuan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaojuan Hu","raw_affiliation_strings":["Enflame-Tech Inc.,Shanghai,China","Enflame-Tech Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc.,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100567886"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63154267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1003","last_page":"1016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983000159263611,"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":0.9983000159263611,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9980999827384949,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8620855808258057},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5656237602233887},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5326561331748962},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4975724518299103},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4514540433883667},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4486076831817627},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4280300438404083},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4057163596153259},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38757285475730896},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35492944717407227},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20199009776115417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620855808258057},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5656237602233887},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5326561331748962},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4975724518299103},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4514540433883667},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4486076831817627},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4280300438404083},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4057163596153259},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38757285475730896},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35492944717407227},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20199009776115417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca56546.2023.10070941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10070941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W1535279741","https://openalex.org/W1686810756","https://openalex.org/W1689711448","https://openalex.org/W1849277567","https://openalex.org/W1901129140","https://openalex.org/W1984993578","https://openalex.org/W1989174502","https://openalex.org/W2022632182","https://openalex.org/W2097117768","https://openalex.org/W2111394443","https://openalex.org/W2112796928","https://openalex.org/W2116175063","https://openalex.org/W2147800946","https://openalex.org/W2194775991","https://openalex.org/W2296646873","https://openalex.org/W2333659671","https://openalex.org/W2483942986","https://openalex.org/W2536587200","https://openalex.org/W2606722458","https://openalex.org/W2612048219","https://openalex.org/W2618530766","https://openalex.org/W2757140470","https://openalex.org/W2786320458","https://openalex.org/W2794670651","https://openalex.org/W2798341898","https://openalex.org/W2798956872","https://openalex.org/W2883882491","https://openalex.org/W2883929540","https://openalex.org/W2888727064","https://openalex.org/W2892817096","https://openalex.org/W2896457183","https://openalex.org/W2898985762","https://openalex.org/W2912012512","https://openalex.org/W2913954081","https://openalex.org/W2927467875","https://openalex.org/W2933147490","https://openalex.org/W2935480346","https://openalex.org/W2943235166","https://openalex.org/W2963446712","https://openalex.org/W2963470893","https://openalex.org/W2964350391","https://openalex.org/W2968713519","https://openalex.org/W2981758446","https://openalex.org/W2982050681","https://openalex.org/W2989604896","https://openalex.org/W3010874605","https://openalex.org/W3012249773","https://openalex.org/W3093176224","https://openalex.org/W3093701126","https://openalex.org/W3097777922","https://openalex.org/W3123639931","https://openalex.org/W3127736057","https://openalex.org/W3157657667","https://openalex.org/W3174529902","https://openalex.org/W3177865674","https://openalex.org/W3187054007","https://openalex.org/W3188176114","https://openalex.org/W3190062760","https://openalex.org/W3190806564","https://openalex.org/W3197720002","https://openalex.org/W3210802685","https://openalex.org/W4214686755","https://openalex.org/W4223511625","https://openalex.org/W4225810502","https://openalex.org/W4231662810","https://openalex.org/W4244894488","https://openalex.org/W4281932226","https://openalex.org/W4287208846","https://openalex.org/W4288346195","https://openalex.org/W4289276774","https://openalex.org/W4293254947","https://openalex.org/W4293584584","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6696492461","https://openalex.org/W6713134421","https://openalex.org/W6748324931","https://openalex.org/W6750227808","https://openalex.org/W6751109714","https://openalex.org/W6751349269","https://openalex.org/W6755207826","https://openalex.org/W6756580189","https://openalex.org/W6761937618","https://openalex.org/W6766978945","https://openalex.org/W6779728309","https://openalex.org/W6784999070","https://openalex.org/W6786565749","https://openalex.org/W6794457956","https://openalex.org/W6798149751"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W121182129"],"abstract_inverted_index":{"Facing":[0],"the":[1,30,36,151,156,161,183,203,213,260],"growing":[2],"complexity":[3],"of":[4,158,243,262],"Deep":[5,38],"Neural":[6],"Networks":[7],"(DNNs),":[8],"high-performance":[9],"and":[10,19,55,73,81,87,96,110,136,144,154,171,175,192,198,236,245,249,251,270],"power-efficient":[11],"AI":[12,52],"accelerators":[13],"are":[14],"desired":[15],"to":[16,113,140],"provide":[17],"effective":[18],"affordable":[20],"cloud":[21],"inference":[22,53],"services.":[23],"We":[24],"introduce":[25],"our":[26,59],"flagship":[27],"product,":[28],"i.e.,":[29],"Cloudblazer":[31,68,231,263],"i20":[32,69,232],"accelerator,":[33],"which":[34],"integrates":[35,92],"innovated":[37],"Thinking":[39],"Unit":[40],"(DTU":[41],"2.0).":[42],"The":[43,257],"design":[44,265],"is":[45,186],"driven":[46],"by":[47],"requests":[48],"drawn":[49],"from":[50,58],"various":[51,229],"applications":[54],"insights":[56],"learned":[57],"previous":[60],"products.":[61],"With":[62],"careful":[63],"tradeoffs":[64],"in":[65,117,228,247,253],"hardware-software":[66],"co-design,":[67],"delivers":[70],"impressive":[71],"performance":[72,204,248],"energy":[74,184,199,254],"efficiency":[75,193],"while":[76],"maintaining":[77],"acceptable":[78],"hardware":[79,153,217],"costs":[80],"software":[82,162],"complexity/flexibility.":[83],"To":[84,149],"tackle":[85],"computation-":[86],"data-intensive":[88],"workloads,":[89],"DTU":[90],"2.0":[91],"powerful":[93],"vector/matrix":[94],"engines":[95],"a":[97,240],"large-capacity":[98],"multi-level":[99],"memory":[100],"hierarchy":[101],"with":[102,212,221,239],"high":[103],"bandwidth.":[104],"It":[105],"supports":[106],"comprehensive":[107],"data":[108,129,131,134,146,172],"flow":[109,173],"synchronization":[111],"patterns":[112],"fully":[114],"exploit":[115],"parallelism":[116],"computation/memory":[118],"access":[119,147],"within":[120],"or":[121,215],"among":[122],"concurrent":[123],"tasks.":[124],"Moreover,":[125],"it":[126],"enables":[127,164],"sparse":[128],"compression/decompression,":[130],"broadcasting,":[132],"repeated":[133],"transfer,":[135],"kernel":[137],"code":[138],"prefetching":[139],"optimize":[141],"bandwidth":[142],"utilization":[143],"reduce":[145],"overheads.":[148],"utilize":[150],"underlying":[152],"simplify":[155],"development":[157],"customized":[159],"DNNs/operators,":[160],"stack":[163],"automatic":[165],"optimizations":[166],"(such":[167],"as":[168],"operator":[169],"fusion":[170],"tuning)":[174],"provides":[176],"diverse":[177],"programming":[178],"interfaces":[179],"for":[180],"developers.":[181],"Lastly,":[182],"consumption":[185],"optimized":[187],"through":[188],"dynamic":[189],"power":[190],"integrity":[191,196],"management,":[194],"eliminating":[195],"risks":[197],"wastes.":[200],"Based":[201],"on":[202],"requirement,":[205],"developers":[206],"also":[207],"can":[208],"assign":[209],"their":[210],"workloads":[211],"entire":[214],"partial":[216],"resources":[218],"accordingly.":[219],"Evaluated":[220],"10":[222],"representative":[223],"DNN":[224],"models":[225],"widely":[226],"adopted":[227],"domains,":[230],"outperforms":[233],"Nvidia":[234],"T4":[235],"A10":[237],"GPUs":[238],"geometric":[241],"mean":[242],"2.22x":[244],"1.16x":[246],"1.04x":[250],"1.17x":[252],"efficiency,":[255,269],"respectively.":[256],"improvements":[258],"demonstrate":[259],"effectiveness":[261],"i20\u2019s":[264],"that":[266],"emphasizes":[267],"performance,":[268],"flexibility.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}