{"id":"https://openalex.org/W4399487416","doi":"https://doi.org/10.1145/3649476.3658811","title":"Performance Analysis of OFA-NAS ResNet Topologies Across Diverse Hardware Compute Units","display_name":"Performance Analysis of OFA-NAS ResNet Topologies Across Diverse Hardware Compute Units","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399487416","doi":"https://doi.org/10.1145/3649476.3658811"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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/A5055771008","display_name":"H C Prashanth","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prashanth H C","raw_affiliation_strings":["IIIT-Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-9650-3731","affiliations":[{"raw_affiliation_string":"IIIT-Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061397479","display_name":"Madhav Rao","orcid":"https://orcid.org/0000-0003-2278-9148"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhav Rao","raw_affiliation_strings":["IIIT-Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0003-2278-9148","affiliations":[{"raw_affiliation_string":"IIIT-Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08239146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"604","last_page":"607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9872999787330627,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.7816773653030396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6594272255897522},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.5132381916046143},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3547689914703369},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3240918517112732},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3053225874900818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13303646445274353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1098380982875824}],"concepts":[{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.7816773653030396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6594272255897522},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.5132381916046143},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3547689914703369},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3240918517112732},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3053225874900818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13303646445274353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1098380982875824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649476.3658811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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":24,"referenced_works":["https://openalex.org/W2810271953","https://openalex.org/W2902313780","https://openalex.org/W2904699287","https://openalex.org/W2932077855","https://openalex.org/W2943899653","https://openalex.org/W2947565354","https://openalex.org/W2951104886","https://openalex.org/W2954234207","https://openalex.org/W2964259004","https://openalex.org/W2994749257","https://openalex.org/W3034681682","https://openalex.org/W3044091840","https://openalex.org/W3049039618","https://openalex.org/W3095058588","https://openalex.org/W3107599876","https://openalex.org/W3158482653","https://openalex.org/W3165698711","https://openalex.org/W4287631196","https://openalex.org/W4287719374","https://openalex.org/W4293309682","https://openalex.org/W4297459708","https://openalex.org/W4300687381","https://openalex.org/W4301260059","https://openalex.org/W4313484911"],"related_works":["https://openalex.org/W2599472179","https://openalex.org/W4323057981","https://openalex.org/W2086397253","https://openalex.org/W2133122801","https://openalex.org/W3178607569","https://openalex.org/W4310870954","https://openalex.org/W4308408209","https://openalex.org/W4301783946","https://openalex.org/W600422426","https://openalex.org/W3196952692"],"abstract_inverted_index":{"Network":[0],"architecture":[1],"search":[2],"(NAS)":[3],"is":[4,35,38],"a":[5,10,15,22,155,189],"tedious":[6],"process":[7],"and":[8,71,91,97,203],"hence":[9],"different":[11],"approach":[12],"to":[13,40,160,172],"train":[14],"large":[16],"over":[17,93,113,176],"parameterized":[18],"network,":[19],"followed":[20],"by":[21],"progressively":[23],"shrinking":[24],"algorithm":[25],"towards":[26],"targeting":[27],"the":[28,83,116,165,182,197],"best":[29],"efficient":[30],"models":[31,131,169,198],"for":[32,56,110,115,147,164,181,201],"hardware":[33,60],"platforms":[34,61],"practiced,":[36],"which":[37],"referred":[39],"as":[41],"Once-For-All":[42],"(OFA)":[43],"network.":[44],"This":[45],"paper":[46],"focuses":[47],"on":[48,53,74,82,136,174,188],"utilizing":[49],"OFA-defined":[50],"NAS":[51,124,167,184],"runs":[52,81],"ResNet":[54,126],"topologies":[55,127],"wide":[57],"range":[58],"of":[59,89,106,121,150,158,196],"ranging":[62],"from":[63],"workstations":[64],"CPU,":[65,68],"GPU,":[66],"mobile":[67,94,98],"GPUs,":[69],"VPU,":[70],"DPU":[72,117],"run":[73,173],"Xilnx":[75,190],"FPGA.":[76],"The":[77,103],"OFA":[78,122,166,183],"extracted":[79,125,185],"model":[80,120,186],"VPU":[84],"unit":[85],"offers":[86,144],"speed":[87],"improvement":[88,105,157],"86%":[90],"46%":[92],"CPU":[95,139],"A76,":[96],"GPU":[99,153],"630":[100],"system":[101],"respectively.":[102],"latency":[104],"100%":[107,161],"was":[108,162],"achieved":[109,163],"3-threaded":[111],"execution":[112,143],"single-thread":[114],"unit.":[118],"Roofline":[119,178],"defined":[123],"indicated":[128],"that":[129,194],"all":[130],"are":[132,199],"compute-bound":[133,200],"when":[134,170],"operated":[135],"Threadripper":[137],"960X":[138],"workstation;":[140],"with":[141],"16-threaded":[142],"maximum":[145],"performance":[146,179],"batch":[148],"size":[149],"16.":[151],"For":[152],"workstation,":[154],"throughput":[156],"66.66%":[159],"generated":[168],"configured":[171],"3-threads":[175],"single-thread.":[177],"analysis":[180],"running":[187],"FPGA":[191],"ZCU102":[192],"showed":[193],"most":[195],"single":[202],"multi-threaded":[204],"execution.":[205]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}