{"id":"https://openalex.org/W4401882216","doi":"https://doi.org/10.1145/3674558.3674562","title":"Layer-wise Exploration of a Neural Processing Unit Compiler's Optimization Space","display_name":"Layer-wise Exploration of a Neural Processing Unit Compiler's Optimization Space","publication_year":2024,"publication_date":"2024-05-15","ids":{"openalex":"https://openalex.org/W4401882216","doi":"https://doi.org/10.1145/3674558.3674562"},"language":"en","primary_location":{"id":"doi:10.1145/3674558.3674562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674558.3674562","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Computer Technology Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3674558.3674562","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008347914","display_name":"Fabrizio Indirli","orcid":"https://orcid.org/0000-0003-2973-4131"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Fabrizio Indirli","raw_affiliation_strings":["Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057121109","display_name":"Andrea Carlo Ornstein","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154781","display_name":"STMicroelectronics (Italy)","ror":"https://ror.org/053bqv655","country_code":"IT","type":"company","lineage":["https://openalex.org/I131827901","https://openalex.org/I4210154781"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Carlo Ornstein","raw_affiliation_strings":["STMicroelectronics, Italy"],"affiliations":[{"raw_affiliation_string":"STMicroelectronics, Italy","institution_ids":["https://openalex.org/I4210154781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047102959","display_name":"Giuseppe Desoli","orcid":"https://orcid.org/0000-0002-3901-0770"},"institutions":[{"id":"https://openalex.org/I4210154781","display_name":"STMicroelectronics (Italy)","ror":"https://ror.org/053bqv655","country_code":"IT","type":"company","lineage":["https://openalex.org/I131827901","https://openalex.org/I4210154781"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Desoli","raw_affiliation_strings":["STMicroelectronics, Italy"],"affiliations":[{"raw_affiliation_string":"STMicroelectronics, Italy","institution_ids":["https://openalex.org/I4210154781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042200315","display_name":"Alessandro Buschini","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154781","display_name":"STMicroelectronics (Italy)","ror":"https://ror.org/053bqv655","country_code":"IT","type":"company","lineage":["https://openalex.org/I131827901","https://openalex.org/I4210154781"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Buschini","raw_affiliation_strings":["STMicroelectronics, Italy"],"affiliations":[{"raw_affiliation_string":"STMicroelectronics, Italy","institution_ids":["https://openalex.org/I4210154781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031461662","display_name":"Cristina Silvano","orcid":"https://orcid.org/0000-0003-1668-0883"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristina Silvano","raw_affiliation_strings":["Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086350616","display_name":"Vittorio Zaccaria","orcid":"https://orcid.org/0000-0001-5685-9795"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vittorio Zaccaria","raw_affiliation_strings":["Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008347914"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":1.4752,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84989735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.7443397641181946},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6989432573318481},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5284742116928101},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4998352527618408},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49779725074768066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4297310709953308},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4215313792228699},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.420320987701416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3800421357154846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.349072128534317},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.343132346868515},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1377321183681488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09926587343215942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443397641181946},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6989432573318481},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5284742116928101},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4998352527618408},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49779725074768066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4297310709953308},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4215313792228699},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.420320987701416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3800421357154846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.349072128534317},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.343132346868515},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1377321183681488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09926587343215942},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3674558.3674562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674558.3674562","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Computer Technology Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1271888","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1271888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3674558.3674562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674558.3674562","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Computer Technology Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W89228883","https://openalex.org/W1986697600","https://openalex.org/W2126105956","https://openalex.org/W2145180784","https://openalex.org/W2563468918","https://openalex.org/W2570343428","https://openalex.org/W2594836184","https://openalex.org/W2798341898","https://openalex.org/W2949251082","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2981758446","https://openalex.org/W3004659153","https://openalex.org/W3012249773","https://openalex.org/W3043387812","https://openalex.org/W3103169341","https://openalex.org/W4394670654"],"related_works":["https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W3146558274","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035","https://openalex.org/W1597127505"],"abstract_inverted_index":{"Given":[0],"the":[1,91,95,99,108,121,125,134,143,174,180,194,198],"increasing":[2],"popularity":[3],"of":[4,26,85,94,98,111,124,131,145,177],"Edge":[5],"AI,":[6],"embedded":[7,162],"neural":[8,27,33,60,86,148,170],"processing":[9],"units":[10],"(NPUs)":[11],"are":[12,44],"gradually":[13],"becoming":[14],"a":[15,115,129],"standard":[16],"feature":[17],"in":[18,77],"microcontrollers":[19],"(MCUs)":[20],"and":[21,154,186,196],"System-on-a-Chip":[22],"(SoCs).":[23],"The":[24,74],"deployment":[25],"networks":[28,149],"on":[29,53],"accelerators":[30],"needs":[31],"specialized":[32],"network":[34,61,72,87,171,178],"compilers":[35,62],"that":[36,118],"incorporate":[37],"graph":[38],"optimization":[39],"stages,":[40],"where":[41],"layer-specific":[42],"transformations":[43],"applied":[45],"to":[46,66,150,193],"reduce":[47],"execution":[48],"latency":[49,185],"or":[50],"memory":[51,155,187],"footprint":[52,188],"platform-specific":[54],"computing":[55,96],"elements.":[56],"For":[57,173],"this":[58,78,105,139],"reason,":[59],"expose":[63],"control":[64],"parameters":[65,89],"be":[67],"tuned":[68],"for":[69,90,133],"each":[70],"individual":[71],"layer.":[73],"challenge":[75],"addressed":[76],"paper":[79],"is":[80],"finding":[81],"an":[82,160],"optimal":[83],"combination":[84],"compilation":[88],"efficient":[92],"utilization":[93],"resources":[97],"target":[100],"hardware":[101],"accelerators.":[102],"To":[103],"address":[104],"task":[106],"despite":[107],"huge":[109],"space":[110],"parameters,":[112],"we":[113],"propose":[114],"greedy":[116],"algorithm":[117],"iterates":[119],"through":[120],"convolutional":[122],"layers":[123],"network,":[126],"while":[127],"preserving":[128],"set":[130,176],"solutions":[132],"preceding":[135],"layers.":[136],"We":[137],"evaluated":[138],"approach":[140],"by":[141,165,189,202],"transforming":[142],"graphs":[144],"some":[146],"popular":[147],"optimize":[151],"their":[152],"performance":[153],"footprint,":[156],"mapping":[157],"them":[158],"onto":[159],"experimental":[161],"NPU":[163],"developed":[164],"STMicroelectronics":[166],"using":[167],"its":[168],"associated":[169],"compiler.":[172],"reported":[175],"models,":[179],"proposed":[181],"technique":[182],"has":[183],"improved":[184],"43%":[190],"approximately":[191],"compared":[192],"baseline":[195],"exceeded":[197],"simulated":[199],"annealing":[200],"heuristics":[201],"15%":[203],"approximately.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
