{"id":"https://openalex.org/W3200067639","doi":"https://doi.org/10.1145/3476994","title":"FLASH: <u>F</u> ast Neura <u>l</u> <u>A</u> rchitecture <u>S</u> earch with <u>H</u> ardware Optimization","display_name":"FLASH: <u>F</u> ast Neura <u>l</u> <u>A</u> rchitecture <u>S</u> earch with <u>H</u> ardware Optimization","publication_year":2021,"publication_date":"2021-09-17","ids":{"openalex":"https://openalex.org/W3200067639","doi":"https://doi.org/10.1145/3476994","mag":"3200067639"},"language":"en","primary_location":{"id":"doi:10.1145/3476994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3476994","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","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/A5108578601","display_name":"Guihong Li","orcid":"https://orcid.org/0000-0001-8537-8632"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guihong Li","raw_affiliation_strings":["The University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043173800","display_name":"Sumit K. Mandal","orcid":"https://orcid.org/0000-0002-9294-1603"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit K. Mandal","raw_affiliation_strings":["University of Wisconsin\u2013Madison, Madison, Wisconsin, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084255924","display_name":"\u00dcmit Y. Ogras","orcid":"https://orcid.org/0000-0002-5045-5535"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit Y. Ogras","raw_affiliation_strings":["University of Wisconsin\u2013Madison, Madison, Wisconsin, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036227385","display_name":"Radu M\u0103rculescu","orcid":"https://orcid.org/0000-0003-1826-7646"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Marculescu","raw_affiliation_strings":["The University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108578601"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.1622,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80832604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"5s","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9915000200271606,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9696000218391418,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9621000289916992,"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":0.8065437078475952},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7057798504829407},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6157983541488647},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5080807209014893},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4994790554046631},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48584434390068054},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4772860109806061},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4769550561904907},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4635097086429596},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4328601658344269},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37350261211395264},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3466063141822815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2734743356704712},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.25960177183151245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065437078475952},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7057798504829407},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6157983541488647},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5080807209014893},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4994790554046631},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48584434390068054},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4772860109806061},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4769550561904907},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4635097086429596},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4328601658344269},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37350261211395264},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3466063141822815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2734743356704712},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.25960177183151245},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3476994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3476994","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3244678969","display_name":null,"funder_award_id":"GRC 2939.001 and 3012.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7493855455","display_name":null,"funder_award_id":"CNS-2007284","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1999085092","https://openalex.org/W2018934112","https://openalex.org/W2108598243","https://openalex.org/W2118231264","https://openalex.org/W2194775991","https://openalex.org/W2518281301","https://openalex.org/W2613989746","https://openalex.org/W2782046614","https://openalex.org/W2795213472","https://openalex.org/W2809171749","https://openalex.org/W2890590696","https://openalex.org/W2945827377","https://openalex.org/W2963163009","https://openalex.org/W2968986602","https://openalex.org/W2971002981","https://openalex.org/W2988304900","https://openalex.org/W3022053993","https://openalex.org/W3035560939","https://openalex.org/W3048606948","https://openalex.org/W3094801149","https://openalex.org/W3101553402","https://openalex.org/W3105888187","https://openalex.org/W3107453328","https://openalex.org/W3185405380","https://openalex.org/W3209828932","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2532502681","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W3154092384","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Neural":[0],"architecture":[1],"search":[2,129],"(NAS)":[3],"is":[4,230,241],"a":[5,31,54,67,127,172,255],"promising":[6],"technique":[7],"to":[8,84,106,152,182,204,244,251],"design":[9],"efficient":[10],"and":[11,44,64,98,113,147,157,193],"high-performance":[12],"deep":[13],"neural":[14],"networks":[15],"(DNNs).":[16],"As":[17,71],"the":[18,26,61,72,79,86,142,154,184,190,197,205,223,227],"performance":[19,65],"requirements":[20],"of":[21,89,126,160,196,219,226],"ML":[22,167],"applications":[23],"grow":[24],"continuously,":[25],"hardware":[27,69,246],"accelerators":[28],"start":[29],"playing":[30],"central":[32],"role":[33],"in":[34,259],"DNN":[35,62,162],"design.":[36],"This":[37,50],"trend":[38],"makes":[39],"NAS":[40,57,109,207,253],"even":[41],"more":[42,132,215],"complicated":[43],"time-consuming":[45],"for":[46],"most":[47],"real":[48,68],"applications.":[49],"paper":[51],"proposes":[52],"FLASH,":[53],"very":[55],"fast":[56],"methodology":[58],"that":[59,239],"co-optimizes":[60],"accuracy":[63,116],"on":[66,141,176,254],"platform.":[70],"main":[73],"theoretical":[74],"contribution,":[75],"we":[76,145,170],"first":[77],"propose":[78],"NN-Degree,":[80],"an":[81,115],"analytical":[82,150],"metric":[83],"quantify":[85],"topological":[87],"characteristics":[88],"DNNs":[90],"with":[91,131],"skip":[92],"connections":[93],"(e.g.,":[94],"DenseNets,":[95],"ResNets,":[96],"Wide-ResNets,":[97],"MobileNets).":[99],"The":[100],"newly":[101],"proposed":[102,210,228],"NN-Degree":[103],"allows":[104],"us":[105,250],"do":[107,252],"training-free":[108],"within":[110],"one":[111],"second":[112],"build":[114],"predictor":[117],"by":[118,138],"training":[119],"as":[120,122],"few":[121],"25":[123],"samples":[124],"out":[125],"vast":[128],"space":[130],"than":[133,216,261],"63":[134],"billion":[135],"configurations.":[136],"Second,":[137],"performing":[139],"inference":[140],"target":[143,198],"hardware,":[144],"fine-tune":[146],"validate":[148],"our":[149,209,235],"models":[151],"estimate":[153],"latency,":[155,192],"area,":[156,191],"energy":[158,194],"consumption":[159,195],"various":[161],"architectures":[163],"while":[164,188],"executing":[165],"standard":[166],"datasets.":[168],"Third,":[169],"construct":[171],"hierarchical":[173,211],"algorithm":[174,213,229],"based":[175],"simplicial":[177],"homology":[178],"global":[179],"optimization":[180],"(SHGO)":[181],"optimize":[183],"model-architecture":[185],"co-design":[186],"process,":[187],"considering":[189],"hardware.":[199],"We":[200],"demonstrate":[201],"that,":[202],"compared":[203],"state-of-the-art":[206],"approaches,":[208],"SHGO-based":[212],"enables":[214],"four":[217],"orders":[218],"magnitude":[220],"speedup":[221],"(specifically,":[222],"execution":[224],"time":[225],"about":[231],"0.1":[232],"seconds).":[233],"Finally,":[234],"experimental":[236],"evaluations":[237],"show":[238],"FLASH":[240],"easily":[242],"transferable":[243],"different":[245],"architectures,":[247],"thus":[248],"enabling":[249],"Raspberry":[256],"Pi-3B":[257],"processor":[258],"less":[260],"3":[262],"seconds.":[263]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}