{"id":"https://openalex.org/W3092319711","doi":"https://doi.org/10.1109/dac18072.2020.9218732","title":"Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration","display_name":"Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3092319711","doi":"https://doi.org/10.1109/dac18072.2020.9218732","mag":"3092319711"},"language":"en","primary_location":{"id":"doi:10.1109/dac18072.2020.9218732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","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/A5101706991","display_name":"Cong Guo","orcid":"https://orcid.org/0000-0002-4479-5525"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Guo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021640619","display_name":"Yangjie Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjie Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023684582","display_name":"Yuhao Zhu","orcid":"https://orcid.org/0000-0002-2802-0578"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Zhu","raw_affiliation_strings":["University of Rochester"],"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056949827","display_name":"Zidong Du","orcid":"https://orcid.org/0000-0002-7603-4210"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zidong Du","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323094","display_name":"Chao Li","orcid":"https://orcid.org/0000-0001-6110-6210"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757927","display_name":"Bin Yao","orcid":"https://orcid.org/0000-0002-6478-4209"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101706991"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.257,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.90218566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8569284677505493},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6410849094390869},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6012378334999084},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.5923930406570435},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5894043445587158},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.517551600933075},{"id":"https://openalex.org/keywords/sma*","display_name":"SMA*","score":0.5154067277908325},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5050960183143616},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4962993264198303},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48755234479904175},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48332926630973816},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.45662012696266174},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42733651399612427},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.41491204500198364},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34155869483947754},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10064557194709778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569284677505493},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6410849094390869},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6012378334999084},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.5923930406570435},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5894043445587158},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.517551600933075},{"id":"https://openalex.org/C161921814","wikidata":"https://www.wikidata.org/wiki/Q493743","display_name":"SMA*","level":2,"score":0.5154067277908325},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5050960183143616},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4962993264198303},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48755234479904175},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48332926630973816},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.45662012696266174},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42733651399612427},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.41491204500198364},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34155869483947754},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10064557194709778},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18072.2020.9218732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1612997784","https://openalex.org/W1979527452","https://openalex.org/W2017369466","https://openalex.org/W2093043622","https://openalex.org/W2147880316","https://openalex.org/W2161825883","https://openalex.org/W2163605009","https://openalex.org/W2334795732","https://openalex.org/W2412782625","https://openalex.org/W2442974303","https://openalex.org/W2540279855","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2791175987","https://openalex.org/W2963150697","https://openalex.org/W2963709005","https://openalex.org/W2963989532","https://openalex.org/W2964253307","https://openalex.org/W3103648783"],"related_works":["https://openalex.org/W2255048617","https://openalex.org/W2092102951","https://openalex.org/W2142204081","https://openalex.org/W1512604874","https://openalex.org/W2140636994","https://openalex.org/W2158982898","https://openalex.org/W1784407820","https://openalex.org/W1975707871","https://openalex.org/W2294545068","https://openalex.org/W2785001802"],"abstract_inverted_index":{"The":[0,117,136,162],"research":[1],"interest":[2],"in":[3,111],"specialized":[4],"hardware":[5],"accelerators":[6,24,110],"for":[7],"deep":[8],"neural":[9],"networks":[10],"(DNN)":[11],"spikes":[12],"recently":[13],"owing":[14],"to":[15,64,85,113,119,155,166],"their":[16],"superior":[17],"performance":[18,168],"and":[19,34,83,101,147,150],"efficiency.":[20],"However,":[21],"today\u2019s":[22],"DNN":[23,65,90,109],"primarily":[25],"focus":[26],"on":[27,88,108],"accelerating":[28],"specific":[29],"\"kernels\"":[30],"such":[31,71],"as":[32,72],"convolution":[33],"matrix":[35],"multiplication,":[36],"which":[37],"are":[38],"vital":[39],"but":[40],"only":[41],"part":[42],"of":[43,125],"an":[44],"end-to-end":[45,115],"DNN-enabled":[46],"application.":[47],"Meaningful":[48],"speedups":[49],"over":[50],"the":[51,89,122,126,131,139,144,148,158,176],"entire":[52],"application":[53],"often":[54],"require":[55],"supporting":[56],"computations":[57],"that":[58,104],"are,":[59],"while":[60,170],"massively":[61],"parallel,":[62],"ill-suited":[63],"accelerators.":[66],"Integrating":[67],"a":[68,73,76,97],"general-purpose":[69,106],"processor":[70],"CPU":[74],"or":[75],"GPU":[77],"incurs":[78],"significant":[79],"data":[80],"movement":[81],"overhead":[82],"leads":[84],"resource":[86],"under-utilization":[87],"accelerators.We":[91],"propose":[92],"Simultaneous":[93],"Multi-mode":[94],"Architecture":[95],"(SMA),":[96],"novel":[98],"architecture":[99,179],"design":[100],"execution":[102,128,134],"model":[103,129],"offers":[105],"programmability":[107],"order":[112],"accelerate":[114],"applications.":[116],"key":[118],"SMA":[120,137,163],"is":[121],"temporal":[123],"integration":[124],"systolic":[127],"with":[130,180],"GPU-like":[132],"SIMD":[133],"model.":[135],"exploits":[138],"common":[140],"components":[141],"shared":[142],"between":[143,157],"systolic-array":[145],"accelerator":[146],"GPU,":[149],"provides":[151],"lightweight":[152],"reconfiguration":[153],"capability":[154],"switch":[156],"two":[159],"modes":[160],"in-situ.":[161],"achieves":[164],"up":[165],"63%":[167],"improvement":[169],"consuming":[171],"23%":[172],"less":[173],"energy":[174],"than":[175],"baseline":[177],"Volta":[178],"TensorCore.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2025-10-10T00:00:00"}