{"id":"https://openalex.org/W4413755314","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130330","title":"Optimizing TCN Inference: A Hardware-Software Co-Design Approach with CGRA Acceleration","display_name":"Optimizing TCN Inference: A Hardware-Software Co-Design Approach with CGRA Acceleration","publication_year":2025,"publication_date":"2025-07-06","ids":{"openalex":"https://openalex.org/W4413755314","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130330"},"language":"en","primary_location":{"id":"doi:10.1109/isvlsi65124.2025.11130330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","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/A5119450550","display_name":"Alessandro Varaldi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alessandro Varaldi","raw_affiliation_strings":["DET"],"affiliations":[{"raw_affiliation_string":"DET","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106752575","display_name":"Alessio Naclerio","orcid":"https://orcid.org/0009-0009-8655-1324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessio Naclerio","raw_affiliation_strings":["DET"],"affiliations":[{"raw_affiliation_string":"DET","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009147665","display_name":"Fabrizio Riente","orcid":"https://orcid.org/0000-0003-4147-1098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabrizio Riente","raw_affiliation_strings":["DET"],"affiliations":[{"raw_affiliation_string":"DET","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077512098","display_name":"Maurizio Zamboni","orcid":"https://orcid.org/0000-0001-8179-5973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maurizio Zamboni","raw_affiliation_strings":["DET"],"affiliations":[{"raw_affiliation_string":"DET","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036441962","display_name":"Mariagrazia Graziano","orcid":"https://orcid.org/0000-0002-8721-9990"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mariagrazia Graziano","raw_affiliation_strings":["Politecnico di Torino,DISAT,Torino,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,DISAT,Torino,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012025330","display_name":"Marco Vacca","orcid":"https://orcid.org/0000-0003-2920-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Vacca","raw_affiliation_strings":["DET"],"affiliations":[{"raw_affiliation_string":"DET","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5119450550"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29964895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9266999959945679,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9266999959945679,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.7908390164375305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728268027305603},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.6821991801261902},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.6197688579559326},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5916847586631775},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5521357655525208},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40804800391197205},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3985891044139862},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.36539745330810547},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3218587040901184},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21904516220092773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12685149908065796}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7908390164375305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728268027305603},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6821991801261902},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.6197688579559326},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5916847586631775},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5521357655525208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40804800391197205},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3985891044139862},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.36539745330810547},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3218587040901184},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21904516220092773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12685149908065796},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isvlsi65124.2025.11130330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1980329590","https://openalex.org/W2039974221","https://openalex.org/W2111619626","https://openalex.org/W2416799949","https://openalex.org/W2550143307","https://openalex.org/W2732358839","https://openalex.org/W2743862539","https://openalex.org/W2995086119","https://openalex.org/W3047418344","https://openalex.org/W3207605537","https://openalex.org/W3210220319","https://openalex.org/W4205438547","https://openalex.org/W4252337780","https://openalex.org/W4283747842","https://openalex.org/W4403279000","https://openalex.org/W4411727189"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2146872326","https://openalex.org/W2518118925","https://openalex.org/W3158825072"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,73,77,99],"hardware-software":[4],"co-design":[5],"approach":[6,132,160],"for":[7,22,32,92,113,138,144],"accelerating":[8],"Temporal":[9],"Convolutional":[10],"Network":[11],"(TCN)":[12],"inference":[13,81,137],"on":[14,98],"resource-constrained":[15],"edge":[16,139],"devices.":[17],"TCNs":[18],"are":[19],"powerful":[20],"models":[21,152],"sequential":[23],"data":[24,68],"analysis,":[25],"but":[26],"their":[27],"computational":[28],"complexity":[29],"poses":[30],"challenges":[31],"deployment":[33,148],"in":[34,133,153],"low-power":[35],"IoT":[36,154],"applications.":[37],"To":[38],"address":[39],"this,":[40],"we":[41,157],"integrate":[42],"the":[43,48,122,128,142,165],"CGRA":[44],"accelerator":[45],"\u201cMage\u201d":[46],"into":[47],"RISC-V-based":[49],"X-HEEP":[50],"platform,":[51],"enabling":[52,134],"efficient":[53,147],"execution":[54],"of":[55,130,149],"dilated":[56],"1D":[57],"convolutions":[58],"through":[59],"tailored":[60],"memory":[61],"access":[62],"optimizations,":[63],"tiling":[64],"strategies,":[65],"and":[66,83,110,116,146,170],"DMA-based":[67],"transfers.":[69],"Our":[70],"methodology":[71],"includes":[72],"PyTorch-based":[74],"training":[75],"pipeline,":[76],"custom":[78],"C":[79],"-based":[80],"engine,":[82],"hardware":[84],"acceleration":[85],"via":[86],"Mage,":[87],"which":[88],"supports":[89],"dynamic":[90],"reconfiguration":[91],"different":[93],"TCN":[94,136],"layers.":[95],"Experimental":[96],"evaluation":[97],"Pynq-Z2":[100],"FPGA":[101],"demonstrates":[102],"significant":[103],"speedups,":[104],"achieving":[105],"up":[106],"to":[107,172],"$69.2":[108],"\\times$":[109,112],"$82.6":[111],"int":[114,117],"16":[115],"8":[118],"configurations,":[119],"respectively,":[120],"across":[121],"entire":[123],"network.":[124],"These":[125],"results":[126],"highlight":[127],"effectiveness":[129],"our":[131,159],"real-time":[135],"analytics,":[140],"paving":[141],"way":[143],"scalable":[145],"deep":[150],"learning":[151],"scenarios.":[155],"While":[156],"validate":[158],"using":[161],"an":[162],"EMG":[163],"dataset,":[164],"proposed":[166],"solution":[167],"is":[168],"general":[169],"applicable":[171],"various":[173],"timeseries":[174],"analytics":[175],"tasks.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}