{"id":"https://openalex.org/W4395065134","doi":"https://doi.org/10.1145/3620666.3651384","title":"SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile","display_name":"SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395065134","doi":"https://doi.org/10.1145/3620666.3651384"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651384","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3620666.3651384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043054935","display_name":"Wei Niu","orcid":"https://orcid.org/0000-0002-2697-7042"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Niu","raw_affiliation_strings":["University of Georgia, Athens, Georgia, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-2697-7042","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, United States of America","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095848513","display_name":"Md Musfiqur Rahman Sanim","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Musfiqur Rahman Sanim","raw_affiliation_strings":["University of Georgia, Athens, Georgia, United States of America"],"raw_orcid":"https://orcid.org/0009-0009-8431-3699","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, United States of America","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011809994","display_name":"Zhihao Shu","orcid":"https://orcid.org/0009-0008-8749-7115"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Shu","raw_affiliation_strings":["University of Georgia, Athens, Georgia, United States of America"],"raw_orcid":"https://orcid.org/0009-0008-8749-7115","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, United States of America","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582412","display_name":"Jiexiong Guan","orcid":"https://orcid.org/0000-0001-5274-9169"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiexiong Guan","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5274-9169","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, United States of America","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University, Raleigh, North Carolina, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3599-8010","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, United States of America","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074398218","display_name":"Miao Yin","orcid":"https://orcid.org/0000-0002-5554-5417"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Yin","raw_affiliation_strings":["University of Texas at Arlington, Arlington, Texas, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5554-5417","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, Texas, United States of America","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014913714","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2609-1428"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0002-2609-1428","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058025888","display_name":"Bin Ren","orcid":"https://orcid.org/0000-0002-4116-5237"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ren","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-4116-5237","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5426,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.96905941,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"916","last_page":"931"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980000257492065,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980000257492065,"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/T11932","display_name":"Wireless Body Area Networks","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11896","display_name":"Opportunistic and Delay-Tolerant Networks","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804568350315094},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7209000587463379},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6981946229934692},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4783056080341339},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38626325130462646},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3544442057609558},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3305676579475403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804568350315094},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7209000587463379},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6981946229934692},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4783056080341339},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38626325130462646},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3544442057609558},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3305676579475403},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3620666.3651384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651384","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.13528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13528","pdf_url":"https://arxiv.org/pdf/2404.13528","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3620666.3651384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651384","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1035795797","display_name":"Collaborative Research: SHF: SMALL: Compile-Parallelize-Schedule-Retarget-Repeat (EASER) Paradigm for Dealing with Extreme Heterogeneity","funder_award_id":"2146873","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1721542772","display_name":"CAREER: Achieving Real-Time Machine Learning with Sparsification-Compilation Co-design","funder_award_id":"2047516","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1830422084","display_name":"SHF: Small: K-Way Speculation for Mapping Applications with Dependencies on Modern HPC Systems","funder_award_id":"2334273","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2350003802","display_name":"Collaborative Research: CSR: Medium: Scaling Secure Serverless Computing on Heterogeneous Datacenters","funder_award_id":"2312207","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3492694979","display_name":"Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)","funder_award_id":"2230944","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4077370309","display_name":"HPC-FAIR: A FRAMEWORK MANAGING DATA AND AI MODELS FOR ANALYZING AND OPTIMIZING SCIENTIFIC APPLICATIONS","funder_award_id":"DESC0021293","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G428946422","display_name":"Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)","funder_award_id":"2341378","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6220518580","display_name":"III: Small: Combinatorial Algorithms for High-dimensional Learning","funder_award_id":"2008557","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6250388392","display_name":"OAC Core: SHF: SMALL: ICURE -- In-situ Analytics with Compressed or Summary Representations for Extreme-Scale Architectures","funder_award_id":"2333899","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6651343091","display_name":"Collaborative Research: SHF:SMALL: Compile-Parallelize-Schedule-Retarget-Repeat (EASER) Paradigm for Dealing with Extreme Heterogeneity","funder_award_id":"2333895","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1997430507","https://openalex.org/W1997449553","https://openalex.org/W2002555321","https://openalex.org/W2108598243","https://openalex.org/W2124711255","https://openalex.org/W2127669603","https://openalex.org/W2194775991","https://openalex.org/W2297325673","https://openalex.org/W2331128040","https://openalex.org/W2468875367","https://openalex.org/W2549139847","https://openalex.org/W2595551253","https://openalex.org/W2626129225","https://openalex.org/W2734941459","https://openalex.org/W2804032941","https://openalex.org/W2889402930","https://openalex.org/W2896457183","https://openalex.org/W2949095675","https://openalex.org/W2963563691","https://openalex.org/W2964283259","https://openalex.org/W2970971581","https://openalex.org/W2999276659","https://openalex.org/W3011199263","https://openalex.org/W3014810041","https://openalex.org/W3025165719","https://openalex.org/W3034429256","https://openalex.org/W3038006402","https://openalex.org/W3038827379","https://openalex.org/W3101962329","https://openalex.org/W3103092912","https://openalex.org/W3138516171","https://openalex.org/W3163649573","https://openalex.org/W3164200338","https://openalex.org/W3171087525","https://openalex.org/W3174529902","https://openalex.org/W3174738881","https://openalex.org/W3177313544","https://openalex.org/W3214835194","https://openalex.org/W4214612132","https://openalex.org/W4214709605","https://openalex.org/W4281758439","https://openalex.org/W4282970339","https://openalex.org/W4283020086","https://openalex.org/W4285294723","https://openalex.org/W4287062814","https://openalex.org/W4287748555","https://openalex.org/W4289081847","https://openalex.org/W4301113013","https://openalex.org/W4312443924","https://openalex.org/W4312933868","https://openalex.org/W4313007769","https://openalex.org/W4318541538","https://openalex.org/W4320060064","https://openalex.org/W4362655426","https://openalex.org/W4376653418","https://openalex.org/W4385801275","https://openalex.org/W4385963463","https://openalex.org/W4386075524","https://openalex.org/W4387321091","https://openalex.org/W4390872693","https://openalex.org/W6639102338","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6754777574","https://openalex.org/W6774015895","https://openalex.org/W6803469875"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W2912421143"],"abstract_inverted_index":{"This":[0,68],"work":[1,135],"is":[2,103,136],"motivated":[3],"by":[4],"recent":[5],"developments":[6],"in":[7,65,147],"Deep":[8],"Neural":[9],"Networks,":[10],"particularly":[11],"the":[12,21,34,58,81,88,107,119],"Transformer":[13],"architectures":[14],"underlying":[15],"applications":[16],"such":[17,129],"as":[18,179,181],"ChatGPT,":[19],"and":[20,41,47,97,112,176,195,198,204],"need":[22],"for":[23,75,127,141],"performing":[24],"inference":[25],"on":[26,30,50,105,162,207],"mobile":[27,148,163],"devices.":[28,149],"Focusing":[29],"emerging":[31],"transformers":[32],"(specifically":[33],"ones":[35],"with":[36,80,173,200],"computationally":[37],"efficient":[38,138],"Swin-like":[39],"architectures)":[40],"large":[42],"models":[43],"(e.g.,":[44],"Stable":[45],"Diffusion":[46],"LLMs)":[48],"based":[49,104],"transformers,":[51],"we":[52],"observe":[53],"that":[54,83,154],"layout":[55,78,91,96],"transformations":[56],"between":[57,118],"computational":[59],"operators":[60,85,108],"cause":[61],"a":[62,72,123],"significant":[63],"slowdown":[64],"these":[66],"applications.":[67],"paper":[69],"presents":[70],"SmartMem,":[71],"comprehensive":[73],"framework":[74],"eliminating":[76],"most":[77],"transformations,":[79],"idea":[82],"multiple":[84],"can":[86],"use":[87],"same":[89],"tensor":[90],"through":[92],"careful":[93],"choice":[94],"of":[95,99,115,125,133,193,202],"implementation":[98],"operations.":[100],"Our":[101,150],"approach":[102],"classifying":[106],"into":[109],"four":[110],"groups,":[111],"considering":[113],"combinations":[114],"producer-consumer":[116],"edges":[117],"operators.":[120],"We":[121],"develop":[122],"set":[124],"methods":[126],"searching":[128],"layouts.":[130],"Another":[131],"component":[132],"our":[134],"developing":[137],"memory":[139,144],"layouts":[140],"2.5":[142],"dimensional":[143],"commonly":[145],"seen":[146],"experimental":[151],"results":[152],"show":[153],"SmartMem":[155,188],"outperforms":[156,196],"5":[157],"state-of-the-art":[158],"DNN":[159],"execution":[160],"frameworks":[161],"devices":[164],"across":[165],"18":[166],"varied":[167],"neural":[168],"networks,":[169],"including":[170],"CNNs,":[171],"Transformers":[172],"both":[174],"local":[175],"global":[177],"attention,":[178],"well":[180],"LLMs.":[182],"In":[183],"particular,":[184],"compared":[185],"to":[186],"DNNFusion,":[187],"achieves":[189],"an":[190],"average":[191],"speedup":[192],"2.8\u00d7,":[194],"TVM":[197],"MNN":[199],"speedups":[201],"6.9\u00d7":[203],"7.9\u00d7,":[205],"respectively,":[206],"average.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-04-24T00:00:00"}