{"id":"https://openalex.org/W4410583693","doi":"https://doi.org/10.23919/date64628.2025.10992860","title":"Axon: A Novel Systolic Array Architecture for Improved Run Time and Energy Efficient GeMM and Conv Operation with On-Chip im2col","display_name":"Axon: A Novel Systolic Array Architecture for Improved Run Time and Energy Efficient GeMM and Conv Operation with On-Chip im2col","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410583693","doi":"https://doi.org/10.23919/date64628.2025.10992860"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10992860","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037120477","display_name":"Md. Mizanur Rahaman Nayan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Mizanur Rahaman Nayan","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078314931","display_name":"Ritik Raj","orcid":"https://orcid.org/0009-0005-1853-6107"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritik Raj","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115861658","display_name":"Gouse Basha Shaik","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gouse Basha Shaik","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034089074","display_name":"Tushar Krishna","orcid":"https://orcid.org/0000-0001-5738-6942"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Krishna","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080526846","display_name":"Azad Naeemi","orcid":"https://orcid.org/0000-0003-4774-9046"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azad J Naeemi","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":5.9441,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96088701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996999979019165,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9955999851226807,"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/systolic-array","display_name":"Systolic array","score":0.7021390795707703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672224402427673},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6432017087936401},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4543260335922241},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4431796073913574},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.44126665592193604},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.41236862540245056},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3947736620903015},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38295215368270874},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.26187270879745483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11622220277786255},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09167948365211487}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.7021390795707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672224402427673},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6432017087936401},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4543260335922241},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4431796073913574},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.44126665592193604},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.41236862540245056},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3947736620903015},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38295215368270874},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.26187270879745483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11622220277786255},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09167948365211487},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10992860","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2346205343","https://openalex.org/W2442974303","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2899644485","https://openalex.org/W2942898010","https://openalex.org/W2945146780","https://openalex.org/W2962780877","https://openalex.org/W3012178976","https://openalex.org/W3012561096","https://openalex.org/W3031172388","https://openalex.org/W3036646298","https://openalex.org/W3040024858","https://openalex.org/W3043406639","https://openalex.org/W3047390932","https://openalex.org/W3091512799","https://openalex.org/W3092319711","https://openalex.org/W3097528158","https://openalex.org/W3113606433","https://openalex.org/W3130554079","https://openalex.org/W3184376546","https://openalex.org/W3186743607","https://openalex.org/W3190062760","https://openalex.org/W3200280098","https://openalex.org/W3213528054","https://openalex.org/W3217357178","https://openalex.org/W4244024631","https://openalex.org/W4280635517","https://openalex.org/W4293024984","https://openalex.org/W4312929963","https://openalex.org/W4381050415","https://openalex.org/W4382203333","https://openalex.org/W4385245566","https://openalex.org/W4386736489","https://openalex.org/W4386763770","https://openalex.org/W6778883912","https://openalex.org/W6798882123"],"related_works":["https://openalex.org/W2065289416","https://openalex.org/W2017236304","https://openalex.org/W3142211975","https://openalex.org/W2115579119","https://openalex.org/W2136854845","https://openalex.org/W1879443270","https://openalex.org/W2018912978","https://openalex.org/W2130914040","https://openalex.org/W2119122672","https://openalex.org/W4292904049"],"abstract_inverted_index":{"General":[0],"matrix":[1],"multiplication":[2],"($GeMM$)":[3],"is":[4],"a":[5,34,53,100],"core":[6],"operation":[7],"in":[8,37,59,120,153,190],"virtually":[9],"all":[10],"AI":[11],"applications.":[12],"Systolic":[13],"array":[14],"(SA)":[15],"based":[16,172],"architectures":[17],"have":[18,161],"shown":[19],"great":[20],"promise":[21],"as$GeMM$hardware":[22],"accelerators":[23],"thanks":[24],"to":[25,42,80,104,150],"their":[26],"speed":[27],"and":[28,112,124,132,147,163,166,176,183,193],"energy":[29,128],"efficiency.":[30],"Unfortunately,":[31],"SAs":[32,60],"incur":[33],"linear":[35],"delay":[36],"filling":[38],"the":[39,67,76,89,115,157,174],"operands,":[40],"due":[41],"unidirectional":[43],"propogation":[44],"via":[45],"pipeline":[46],"latches.":[47],"In":[48,87,137],"this":[49],"work,":[50],"we":[51,62],"propose":[52],"novel":[54,175],"in-array":[55],"data":[56,64,91,140,158],"orchestration":[57,92,141],"technique":[58],"where":[61],"enable":[63],"feeding":[65],"on":[66,135,173],"principal":[68],"diagonal":[69],"followed":[70],"by":[71,78],"bi-directional":[72],"propagation.":[73],"This":[74],"improves":[75],"runtime":[77],"up":[79],"2":[81],"\u00d7":[82,126],"at":[83],"minimal":[84],"hardware":[85,102,146,154],"overhead.":[86],"addition,":[88],"proposed":[90,187],"enables":[93],"convolution":[94],"lowering":[95],"(known":[96],"as":[97],"im2col)":[98],"using":[99,179],"simple":[101],"support":[103],"fully":[105],"exploit":[106],"input":[107],"feature":[108],"map":[109],"reuse":[110],"opportunity":[111],"significantly":[113],"lower":[114],"off-chip":[116],"memory":[117],"traffic":[118],"resulting":[119],"1.2":[121],"\u00d7throughput":[122],"improvement":[123],"2.17":[125],"inference":[127],"reduction":[129],"during":[130],"YOLOv3":[131],"RESNET50":[133],"workload":[134],"average.":[136],"contrast,":[138],"conventional":[139,177],"would":[142],"require":[143],"more":[144],"elaborate":[145],"control":[148],"signals":[149],"implement":[151],"im2col":[152],"because":[155],"of":[156],"skew.":[159],"We":[160],"synthesized":[162],"conducted":[164],"place":[165],"route":[167],"for":[168],"16\u00d716":[169],"systolic":[170],"arrays":[171],"orchestrations":[178],"ASAP":[180],"7nm":[181],"PDK":[182],"found":[184],"that":[185],"our":[186],"approach":[188],"results":[189],"0.211%":[191],"area":[192],"1.6%":[194],"power":[195],"overheads.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}