{"id":"https://openalex.org/W4415594459","doi":"https://doi.org/10.1109/tc.2025.3623868","title":"A Transverse-Read-Assisted Fast Valid-Bits Collection in Stochastic Computing MACs for Energy-Efficient in-RTM DNNs","display_name":"A Transverse-Read-Assisted Fast Valid-Bits Collection in Stochastic Computing MACs for Energy-Efficient in-RTM DNNs","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415594459","doi":"https://doi.org/10.1109/tc.2025.3623868"},"language":null,"primary_location":{"id":"doi:10.1109/tc.2025.3623868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3623868","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","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/A5038618940","display_name":"Jihe Wang","orcid":"https://orcid.org/0000-0003-0499-0999"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihe Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-0499-0999","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiying Zhang","orcid":"https://orcid.org/0009-0004-4832-540X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiying Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-4832-540X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114190812","display_name":"Xingwu Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133467","display_name":"Xi'an Aeronautical University","ror":"https://ror.org/03qn8zy63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210133467"]},{"id":"https://openalex.org/I4210141776","display_name":"China XD Group (China)","ror":"https://ror.org/04ceqst84","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210141776"]},{"id":"https://openalex.org/I4210147525","display_name":"AviChina Industry & Technology (China)","ror":"https://ror.org/05j26dk60","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210147525"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwu Dong","raw_affiliation_strings":["AVIC XI’an Aeronautics Computing Technique Research Institute,, Xi’an, China","AVIC ACTRI, China"],"raw_orcid":"https://orcid.org/0009-0004-9707-1119","affiliations":[{"raw_affiliation_string":"AVIC XI’an Aeronautics Computing Technique Research Institute,, Xi’an, China","institution_ids":["https://openalex.org/I4210133467","https://openalex.org/I4210141776"]},{"raw_affiliation_string":"AVIC ACTRI, China","institution_ids":["https://openalex.org/I4210147525"]}]},{"author_position":"last","author":{"id":null,"display_name":"Danghui Wang","orcid":"https://orcid.org/0000-0002-9058-8498"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danghui Wang","raw_affiliation_strings":["Embedded System Integration Engineering Center of the Ministry of Education, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-9058-8498","affiliations":[{"raw_affiliation_string":"Embedded System Integration Engineering Center of the Ministry of Education, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration, Ministry of Education, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25638411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"1","first_page":"13","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9959999918937683,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9959999918937683,"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":0.9939000010490417,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/interleaving","display_name":"Interleaving","score":0.7530999779701233},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.720300018787384},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6615999937057495},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5343000292778015},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4648999869823456},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4406999945640564},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.42289999127388},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.3732999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704000115394592},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.7530999779701233},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.720300018787384},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6615999937057495},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6123999953269958},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.42289999127388},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2780971903","wikidata":"https://www.wikidata.org/wiki/Q2933705","display_name":"Stochastic computing","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2025.3623868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3623868","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7254467870","display_name":null,"funder_award_id":"62272393","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2056999868","https://openalex.org/W2066877279","https://openalex.org/W2112796928","https://openalex.org/W2119092821","https://openalex.org/W2183341477","https://openalex.org/W2583522611","https://openalex.org/W2792740111","https://openalex.org/W2805638497","https://openalex.org/W2900009113","https://openalex.org/W2913174568","https://openalex.org/W2943147624","https://openalex.org/W2955242165","https://openalex.org/W3047076889","https://openalex.org/W3091279293","https://openalex.org/W3092331354","https://openalex.org/W3148210779","https://openalex.org/W3184640448","https://openalex.org/W4200495212","https://openalex.org/W4213061603","https://openalex.org/W4285178986","https://openalex.org/W4308083597","https://openalex.org/W4322624379","https://openalex.org/W4379115954","https://openalex.org/W4386764616","https://openalex.org/W4390691973"],"related_works":[],"abstract_inverted_index":{"It":[0],"looks":[1],"very":[2],"attractive":[3],"to":[4,12,91,137,159],"coordinate":[5],"racetrack-memory":[6],"(RM)":[7],"and":[8],"stochastic-computing":[9],"(SC)":[10],"jointly":[11],"build":[13,92],"an":[14,93,151,180,202],"ultra-low":[15],"power":[16],"neuron-architecture.":[17],"However,":[18,179],"the":[19,31,48,108,117,126,145,148,161,165,194,197,212,223],"above":[20],"combination":[21],"has":[22],"always":[23],"been":[24],"questioned":[25],"in":[26,163,172],"a":[27,55,61,71,76,85,130],"fatal":[28],"weakness":[29],"that":[30,87,222],"heavy":[32],"valid-bits":[33,65,95,166,177],"collection":[34,63,96],"of":[35,64,73,154,183,196,211],"Racetrack":[36],"Memory-Magnetic":[37],"Tunnel":[38],"Junctions(RM-MTJ),":[39],"a.k.a.":[40],"accumulative":[41],"parallel":[42,89,149,198],"counters":[43],"(APCs),":[44],"cannot":[45,188],"physically":[46],"match":[47],"requirement":[49],"for":[50,104,120,175,208],"energy-efficient":[51],"in-memory":[52],"DNNs.":[53],"Fortunately,":[54],"recently":[56],"developed":[57],"Transverse-Read":[58],"(TR)":[59],"provides":[60],"lightweight":[62],"by":[66,125,141,147,242],"detecting":[67],"domain-wall":[68],"resistance":[69],"between":[70],"couple":[72],"MTJs":[74],"on":[75],"single":[77],"nanowire.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"first":[83],"propose":[84],"neuron-architecture":[86],"utilizes":[88],"TRs":[90],"ultra-fast":[94],"scheme":[97],"specifically":[98],"targeted":[99],"at":[100],"Multiply-Accumulate":[101],"(MAC)":[102],"units":[103],"in-RTM":[105],"DNNs,":[106],"where":[107],"multiplication":[109],"operation":[110],"inherently":[111],"involves":[112],"two":[113],"operands.":[114],"To":[115,143],"solve":[116],"huge":[118],"storage":[119],"full":[121,209],"stochastic":[122,139],"sequences":[123,140],"caused":[124],"limited":[127],"TR":[128,155,227],"banks,":[129],"hybrid":[131],"coding,":[132],"pseudo-fractal":[133],"compression,":[134],"is":[135,156,206],"designed":[136,158],"generate":[138],"segments.":[142],"overcome":[144],"misalignment":[146],"early-termination,":[150],"asynchronous":[152],"schedule":[153],"further":[157],"regularize":[160],"vectorization,":[162],"which":[164],"from":[167],"different":[168,216],"lanes":[169],"are":[170],"merged":[171],"multiple":[173],"RM-stacks":[174],"vector-level":[176],"collection.":[178],"inherent":[181],"defect":[182],"TR,":[184],"i.e.,":[185],"neighbor":[186],"parts":[187],"be":[189],"accessed":[190],"simultaneously,":[191],"could":[192],"limit":[193],"throughput":[195],"vector":[199],"multiplication,":[200],"therefore,":[201],"interleaving":[203],"data":[204],"placement":[205],"used":[207],"utilization":[210],"memory":[213],"bus":[214],"among":[215],"vectors.":[217],"The":[218],"experimental":[219],"results":[220],"demonstrate":[221],"SC-MAC":[224],"architecture":[225],"with":[226],"achieves":[228],"2.88\u00d7-4.40\u00d7":[229],"speedup":[230],"over":[231],"CORUSCANT":[232],"(the":[233],"state-of-the-art":[234],"processin-RM":[235],"architecture),":[236],"while":[237],"simultaneously":[238],"reducing":[239],"energy":[240],"consumption":[241],"1.26\u00d7-1.42\u00d7.":[243]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-28T00:00:00"}