{"id":"https://openalex.org/W4399677075","doi":"https://doi.org/10.1145/3673654","title":"SAL: Optimizing the Dataflow of Spin-based Architectures for Lightweight Neural Networks","display_name":"SAL: Optimizing the Dataflow of Spin-based Architectures for Lightweight Neural Networks","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399677075","doi":"https://doi.org/10.1145/3673654"},"language":"en","primary_location":{"id":"doi:10.1145/3673654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673654","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673654","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673654","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020072616","display_name":"Yunping Zhao","orcid":"https://orcid.org/0000-0002-5600-3740"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunping Zhao","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, National University of Defense Technology, changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5600-3740","affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, National University of Defense Technology, changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760813","display_name":"Sheng Ma","orcid":"https://orcid.org/0000-0003-1710-4060"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Ma","raw_affiliation_strings":["School of Computer, National University of Defense Technology, changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1710-4060","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057739949","display_name":"Hengzhu Liu","orcid":"https://orcid.org/0000-0003-4912-0364"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengzhu Liu","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4912-0364","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9743-2034","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.5993,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60855138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998999834060669,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9988999962806702,"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/dataflow","display_name":"Dataflow","score":0.9524564146995544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.86771559715271},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.7981488704681396},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.65228271484375},{"id":"https://openalex.org/keywords/crossbar-switch","display_name":"Crossbar switch","score":0.599003255367279},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5788006782531738},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5636125206947327},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5417658686637878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4570979177951813},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4391144812107086},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42630574107170105},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40076884627342224},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3586706519126892},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32760024070739746},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2842569053173065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13892731070518494}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9524564146995544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86771559715271},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.7981488704681396},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.65228271484375},{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.599003255367279},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5788006782531738},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5636125206947327},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5417658686637878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4570979177951813},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4391144812107086},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42630574107170105},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40076884627342224},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3586706519126892},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32760024070739746},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2842569053173065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13892731070518494},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673654","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673654","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3673654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673654","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673654","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2739656968","display_name":null,"funder_award_id":"62172430, U22A2027,62172155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399677075.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2035385641","https://openalex.org/W2048266589","https://openalex.org/W2096199318","https://openalex.org/W2164819109","https://openalex.org/W2289252105","https://openalex.org/W2334564994","https://openalex.org/W2403784446","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2531409750","https://openalex.org/W2540697258","https://openalex.org/W2559306271","https://openalex.org/W2581348070","https://openalex.org/W2735639288","https://openalex.org/W2798544842","https://openalex.org/W2883780447","https://openalex.org/W2907579173","https://openalex.org/W2934823379","https://openalex.org/W2945146780","https://openalex.org/W2945854677","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W2997462720","https://openalex.org/W2997869757","https://openalex.org/W3003821665","https://openalex.org/W3007021488","https://openalex.org/W3012504067","https://openalex.org/W3105606255","https://openalex.org/W3162993841","https://openalex.org/W3166036439","https://openalex.org/W3184376546","https://openalex.org/W3217357178","https://openalex.org/W4210956562","https://openalex.org/W4224903054","https://openalex.org/W4254300870","https://openalex.org/W4285194374","https://openalex.org/W4293236956","https://openalex.org/W4312141825","https://openalex.org/W4360831836","https://openalex.org/W4381050415","https://openalex.org/W4385221021","https://openalex.org/W4385255585","https://openalex.org/W4388671982","https://openalex.org/W4391222306","https://openalex.org/W6774638715"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W4377693460","https://openalex.org/W2783505431","https://openalex.org/W2033683327","https://openalex.org/W2521947294","https://openalex.org/W2807127337"],"abstract_inverted_index":{"As":[0],"the":[1,11,21,33,44,58,65,73,85,91,104,116,151,155,161,166,171,175,184,191,199,205,208,212,216,228,231,235,243,251,258,261,268,283,293,297,299,302],"Convolutional":[2],"Neural":[3],"Network":[4],"(CNN)":[5],"goes":[6],"deeper":[7],"and":[8,15,27,41,77,99,122,158,211,223,241,266,276],"more":[9,291],"complex,":[10],"network":[12,24],"becomes":[13],"memory-intensive":[14],"computation-intensive.":[16],"To":[17,183],"address":[18,68],"this":[19,69,189],"issue,":[20],"lightweight":[22],"neural":[23,109,138],"reduces":[25,170,242,260],"parameters":[26],"Multiplication-and-Accumulation":[28],"(MAC)":[29],"operations":[30],"by":[31,125,147,238,246,264,270,305],"using":[32],"Depthwise":[34],"Separable":[35],"Convolution":[36],"(DSC)":[37],"to":[38,57,67,72,95,154,174,194,218],"improve":[39],"speed":[40],"efficiency.":[42,82],"Nonetheless,":[43],"energy":[45,81,120,262,303],"efficiency":[46,121,287,304],"of":[47,75,108,118,186,207,308],"classical":[48],"Von":[49],"Neumann":[50,256],"architectures":[51,63,89],"for":[52,136,198],"CNNs":[53],"is":[54,190],"limited":[55],"due":[56,173],"memory":[59,76],"wall":[60],"challenge.":[61],"Spin-based":[62,134],"have":[64],"potential":[66],"challenge":[70],"thanks":[71],"integration":[74],"computing":[78],"with":[79,90,250,296],"ultra-high":[80],"However,":[83],"deploying":[84,227],"DSC":[86],"on":[87,133,215],"spin-based":[88,209,254],"traditional":[92],"dataflow":[93,132,143,168,197,217,233],"leads":[94],"huge":[96],"activation":[97],"movements":[98],"low":[100],"hardware":[101,236],"utilization.":[102],"Moreover,":[103,165,282],"inter-layer":[105,162],"data":[106,163,176,221,244],"dependency":[107,177],"networks":[110,139],"increases":[111],"latency.":[112],"These":[113],"factors":[114],"become":[115],"bottleneck":[117],"improving":[119],"performance.":[123,182],"Inspired":[124],"these":[126],"challenges,":[127],"we":[128],"propose":[129],"a":[130,253],"novel":[131,142,167,232],"Architectures":[135],"Lightweight":[137],"(SAL).":[140],"The":[141],"replaces":[144],"convolution":[145,156],"unrolling":[146],"selecting":[148],"activations":[149],"in":[150],"crossbar":[152,210],"according":[153],"window":[157],"also":[159,169,203],"realizes":[160],"reuse.":[164],"latency":[172],"between":[178],"layers,":[179],"realizing":[180],"higher":[181],"best":[185],"our":[187],"knowledge,":[188],"first":[192],"design":[193],"use":[195],"hybrid":[196],"PIM":[200],"architecture.":[201],"We":[202],"optimize":[204],"structure":[206],"pipeline":[213],"based":[214],"achieve":[219],"better":[220],"reuse":[222],"computational":[224],"parallelism.":[225],"For":[226],"MobileNet":[229],"V1,":[230],"improves":[234,267,285,301],"utilization":[237],"23\u00d7\u223c":[239],"105\u00d7":[240],"traffic":[245],"1.09\u00d7\u223c":[247],"18.6\u00d7.":[248],"Compared":[249,295],"NEBULA,":[252],"non-Von":[255],"architecture,":[257],"SAL":[259,284,300],"consumption":[263],"4\u00d7":[265],"performance":[269],"7.3\u00d7,":[271],"which":[272],"are":[273],"0.32":[274],"mJ":[275],"10.43":[277],"GOPs":[278],"-1":[279],",":[280],"respectively.":[281],"power":[286],"over":[288],"29":[289],"times":[290],"than":[292],"NEBULA.":[294],"Eyeriss,":[298],"four":[306],"orders":[307],"magnitude.":[309]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}