{"id":"https://openalex.org/W4312960084","doi":"https://doi.org/10.1109/lca.2022.3215718","title":"Characterizing and Understanding End-to-End Multi-Modal Neural Networks on GPUs","display_name":"Characterizing and Understanding End-to-End Multi-Modal Neural Networks on GPUs","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4312960084","doi":"https://doi.org/10.1109/lca.2022.3215718"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2022.3215718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3215718","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","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/A5108240316","display_name":"Xiaofeng Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I2800906782","display_name":"Hong Kong Science and Technology Parks Corporation","ror":"https://ror.org/05q8mqd91","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I2800906782"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaofeng Hou","raw_affiliation_strings":["AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong"],"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong","institution_ids":["https://openalex.org/I2800906782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101563311","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0002-4062-3558"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656307","display_name":"Jiacheng Liu","orcid":"https://orcid.org/0000-0003-0378-2311"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102412189","display_name":"Xuehan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehan Tang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188024","display_name":"Lingyu Sun","orcid":"https://orcid.org/0000-0002-1326-2654"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Sun","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323095","display_name":"Chao Li","orcid":"https://orcid.org/0000-0001-6218-4659"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077687075","display_name":"Kwang\u2010Ting Cheng","orcid":"https://orcid.org/0000-0002-3885-4912"},"institutions":[{"id":"https://openalex.org/I2800906782","display_name":"Hong Kong Science and Technology Parks Corporation","ror":"https://ror.org/05q8mqd91","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I2800906782"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kwang-Ting Cheng","raw_affiliation_strings":["AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong"],"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong","institution_ids":["https://openalex.org/I2800906782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108240316"],"corresponding_institution_ids":["https://openalex.org/I2800906782"],"apc_list":null,"apc_paid":null,"fwci":1.2074,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80480805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"21","issue":"2","first_page":"125","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10320","display_name":"Neural Networks and Applications","score":0.9969000220298767,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8605077266693115},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6516872048377991},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.644212007522583},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6075451374053955},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5961893200874329},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.538112461566925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.515693724155426},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4519384801387787},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43570899963378906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39680933952331543},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3548766076564789},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12447282671928406},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07380694150924683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605077266693115},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6516872048377991},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.644212007522583},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6075451374053955},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5961893200874329},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.538112461566925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515693724155426},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4519384801387787},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43570899963378906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39680933952331543},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3548766076564789},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12447282671928406},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07380694150924683},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2022.3215718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3215718","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125712","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85140746946&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G251012422","display_name":null,"funder_award_id":"62122053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2619383789","https://openalex.org/W2945856475","https://openalex.org/W2985076077","https://openalex.org/W3043571714","https://openalex.org/W3100741579","https://openalex.org/W3129568573","https://openalex.org/W3130716829","https://openalex.org/W4221138647","https://openalex.org/W6733328719","https://openalex.org/W6748636330","https://openalex.org/W6797781246"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2615259895","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4231453522","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W2131630752"],"abstract_inverted_index":{"Multi-modal":[0],"neural":[1,60],"networks":[2],"have":[3],"become":[4],"increasingly":[5],"pervasive":[6],"in":[7,42],"many":[8,25],"machine":[9],"learning":[10],"application":[11],"domains":[12],"due":[13],"to":[14],"their":[15,72],"superior":[16],"accuracy":[17],"by":[18],"fusing":[19],"various":[20],"modalities.":[21],"However,":[22],"they":[23],"present":[24,53],"unique":[26],"characteristics":[27],"such":[28],"as":[29],"multi-stage":[30],"execution,":[31],"frequent":[32],"synchronization":[33],"and":[34,45,54,77,91],"high":[35],"heterogeneity,":[36],"which":[37],"are":[38],"not":[39],"well":[40],"understood":[41],"the":[43],"system":[44,76],"architecture":[46,78],"community.":[47],"In":[48],"this":[49],"article,":[50],"we":[51],"first":[52],"characterize":[55],"a":[56],"set":[57],"of":[58,63,96],"multi-modal":[59,97],"network":[61],"workloads":[62],"different":[64],"sizes":[65],"at":[66],"inference":[67,95],"stage.":[68],"We":[69,80],"then":[70],"explore":[71],"important":[73],"implications":[74],"from":[75],"aspects.":[79],"hope":[81],"that":[82],"our":[83],"work":[84],"can":[85],"help":[86],"guide":[87],"future":[88],"software/hardware":[89],"design":[90],"optimization":[92],"for":[93],"efficient":[94],"DNN":[98],"applications.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
