{"id":"https://openalex.org/W7161970909","doi":"https://doi.org/10.48550/arxiv.2605.20802","title":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","display_name":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161970909","doi":"https://doi.org/10.48550/arxiv.2605.20802"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136707941","display_name":"Kang You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136614583","display_name":"Chen Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136622391","display_name":"Lee Jun Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Lee Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072186998","display_name":"Ziling Wei","orcid":"https://orcid.org/0000-0002-7858-1445"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Ziling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136624216","display_name":"Cheng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101743779","display_name":"Zekai Xu","orcid":"https://orcid.org/0000-0002-8462-574X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zekai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136656206","display_name":"Yu Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019717600","display_name":"Honglan Jiang","orcid":"https://orcid.org/0000-0003-3705-4240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Honglan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036755436","display_name":"Zhezhi He","orcid":"https://orcid.org/0000-0002-6357-236X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zhezhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.96670001745224,"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":0.96670001745224,"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":0.008700000122189522,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.007799999788403511,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7705000042915344},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.763700008392334},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.593999981880188},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5764999985694885},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5703999996185303},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.5595999956130981},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5442000031471252},{"id":"https://openalex.org/keywords/neuromorphic-engineering","display_name":"Neuromorphic engineering","score":0.5375999808311462},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.5375000238418579},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4851999878883362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276000022888184},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7705000042915344},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.763700008392334},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.5595999956130981},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.5375999808311462},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.5375000238418579},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4846999943256378},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.36570000648498535},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C67212190","wikidata":"https://www.wikidata.org/wiki/Q104851","display_name":"Firmware","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9069029092788696}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"neural":[1,197],"networks":[2,198],"(SNNs)":[3],"exploit":[4,172],"event-driven":[5,184],"and":[6,87,115,162,171,178,212,223,226],"addition-only":[7],"computation":[8,185],"to":[9,26,31,119,138,155,167],"substantially":[10,134],"improve":[11],"efficiency":[12,216,229],"for":[13],"intelligent":[14],"computation.":[15],"A":[16],"key":[17],"temporal":[18],"property":[19],"of":[20,91,159],"SNNs,":[21],"elastic":[22,92,108],"inference,":[23],"allows":[24],"outputs":[25,51],"emerge":[27],"progressively,":[28],"enabling":[29],"responses":[30],"salient":[32],"inputs":[33],"much":[34],"earlier":[35],"than":[36],"full":[37],"evaluation.":[38],"However,":[39],"existing":[40],"SNN-specific":[41],"accelerators":[42],"cannot":[43],"capitalize":[44],"on":[45,62],"this":[46,144],"property.":[47],"Layer-by-layer":[48],"designs":[49,60],"emit":[50],"only":[52],"after":[53],"all":[54,69],"layers":[55],"are":[56],"complete,":[57],"while":[58,200],"time-step-by-time-step":[59],"rely":[61],"coarse-grained,":[63],"layer-wise":[64],"pipelines":[65],"that":[66,105,133,191],"require":[67],"synchronizing":[68],"spines/tokens":[70],"within":[71],"a":[72,101,111,129,149,205],"layer.":[73],"This":[74],"barrier":[75],"prevents":[76],"results":[77],"from":[78],"being":[79],"forwarded":[80],"immediately,":[81],"delaying":[82],"the":[83,89,136,139,218,232],"earliest":[84],"possible":[85],"response":[86],"forfeiting":[88],"benefits":[90],"inference.":[93],"To":[94,142],"address":[95,151],"these":[96],"challenges,":[97],"we":[98],"propose":[99],"ELSA,":[100],"near-SRAM":[102],"dataflow":[103],"architecture":[104],"realizes":[106],"true":[107],"inference":[109],"through":[110],"fine-grained":[112],"spine/token-wise":[113],"pipeline":[114,132],"hardware":[116],"optimizations":[117],"tailored":[118],"SNNs.":[120],"ELSA":[121,147,181,208],"forwards":[122],"each":[123],"spine/token":[124],"immediately":[125],"upon":[126],"production,":[127],"forming":[128],"continuous":[130],"streaming":[131],"reduces":[135],"latency":[137],"first":[140],"response.":[141],"enhance":[143],"lightweight":[145],"execution,":[146],"introduces":[148],"bundled":[150],"event":[152],"representation":[153],"protocol":[154],"lower":[156],"communication":[157],"traffic":[158],"network-on-chip":[160],"(NoC),":[161],"leverages":[163],"mini-batch":[164],"spiking":[165],"Gustavson-product":[166],"cut":[168],"memory":[169],"access":[170],"inherent":[173],"sparsity.":[174],"Combined":[175],"with":[176],"mapping":[177],"scheduling":[179],"optimizations,":[180],"achieves":[182,209],"efficient,":[183],"without":[186],"compromising":[187],"accuracy.":[188,203],"Experiments":[189],"show":[190],"SNNs":[192],"can":[193],"outperform":[194],"quantized":[195],"artificial":[196],"(QANNs)":[199],"maintaining":[201],"on-par":[202],"For":[204],"4-bit":[206],"ResNet-50,":[207],"3.4$\\times$":[210],"speedup":[211,225],"13.6$\\times$":[213],"higher":[214],"energy":[215,228],"over":[217,231],"SOTA":[219,233],"QANN":[220],"accelerator":[221,235],"(ANT),":[222],"2.9$\\times$":[224],"22.1$\\times$":[227],"gains":[230],"SNN":[234],"(PAICORE).":[236]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}