{"id":"https://openalex.org/W4389166707","doi":"https://doi.org/10.1109/iccad57390.2023.10323836","title":"PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning","display_name":"PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389166707","doi":"https://doi.org/10.1109/iccad57390.2023.10323836"},"language":"en","primary_location":{"id":"doi:10.1109/iccad57390.2023.10323836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","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/A5072580709","display_name":"Jialin Cao","orcid":"https://orcid.org/0009-0001-9054-5500"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Cao","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113058728","display_name":"Xuanda Lin","orcid":"https://orcid.org/0009-0009-6355-2439"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanda Lin","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113426367","display_name":"Manting Zhang","orcid":"https://orcid.org/0009-0007-7437-6587"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Manting Zhang","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102312689","display_name":"Kejia Shi","orcid":"https://orcid.org/0009-0001-8471-0995"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejia Shi","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614702","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0001-5008-2153"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015932760","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-7288-1789"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Lab of ASIC &#x0026; System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9933000206947327,"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":0.7214838266372681},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6221968531608582},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6120983958244324},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5789517760276794},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5646077394485474},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4345852732658386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42662250995635986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4036228656768799},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3897785544395447},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2728179097175598},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10470172762870789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214838266372681},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6221968531608582},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6120983958244324},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5789517760276794},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5646077394485474},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4345852732658386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42662250995635986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4036228656768799},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3897785544395447},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2728179097175598},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10470172762870789},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad57390.2023.10323836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6507269736","display_name":null,"funder_award_id":"2021YFA1003602","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2276892413","https://openalex.org/W2324238275","https://openalex.org/W2896457183","https://openalex.org/W2899244816","https://openalex.org/W2915106038","https://openalex.org/W2923014074","https://openalex.org/W2970500560","https://openalex.org/W2979826702","https://openalex.org/W2996874060","https://openalex.org/W2998342322","https://openalex.org/W3012178976","https://openalex.org/W3017024317","https://openalex.org/W3025085339","https://openalex.org/W3083389787","https://openalex.org/W3092513807","https://openalex.org/W3100980998","https://openalex.org/W3104401858","https://openalex.org/W3104849992","https://openalex.org/W3130240120","https://openalex.org/W3132616766","https://openalex.org/W3155487259","https://openalex.org/W3159727696","https://openalex.org/W3162542754","https://openalex.org/W3174862672","https://openalex.org/W3176468986","https://openalex.org/W3189877953","https://openalex.org/W3205192296","https://openalex.org/W3206453033","https://openalex.org/W3206837665","https://openalex.org/W3207622241","https://openalex.org/W3213174544","https://openalex.org/W4214686755","https://openalex.org/W4291653336","https://openalex.org/W4312569226","https://openalex.org/W4383749557","https://openalex.org/W4385245566","https://openalex.org/W6677580257","https://openalex.org/W6755207826","https://openalex.org/W6780125659"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"Transformer":[0,82],"models":[1,83],"have":[2,49,108],"been":[3,50],"widely":[4],"adopted":[5],"in":[6,64,138,158],"the":[7,19,26,65,90],"field":[8],"of":[9,22,28,67],"Natural":[10],"Language":[11],"Processing":[12],"(NLP)":[13],"and":[14,32,153,162],"Computer":[15],"Vision":[16],"(CV).":[17],"However,":[18,52],"excellent":[20],"performance":[21],"Transformers":[23,38],"comes":[24],"at":[25],"cost":[27],"heavy":[29],"memory":[30],"footprints":[31],"gigantic":[33],"computing":[34,117],"complexity.":[35],"To":[36],"deploy":[37,81],"on":[39,84],"resource":[40],"constrained":[41],"platforms,":[42],"e.g.,":[43],"FPGA,":[44],"diverse":[45],"weight":[46],"pruning":[47,58,100,123],"strategies":[48],"proposed.":[51],"pattern":[53,87,95,122],"pruning,":[54,96],"as":[55],"an":[56],"alternative":[57],"method,":[59],"is":[60],"not":[61],"well":[62],"explored":[63],"context":[66],"Transformers.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,93,107],"propose":[73],"PP-Transformer,":[74],"a":[75,97,110,115],"framework":[76],"specifically":[77],"designed":[78],"to":[79,102,120,133,160],"efficiently":[80],"FPGA":[85],"using":[86],"pruning.":[88],"At":[89],"algorithm":[91,130],"level,":[92],"leverage":[94],"coarse-grained":[98],"structured":[99],"strategy,":[101],"reduce":[103],"parameter":[104,139],"storage.":[105],"Meanwhile,":[106],"developed":[109],"dedicated":[111],"hardware":[112,147],"architecture,":[113],"featuring":[114],"custom":[116],"engine":[118],"tailored":[119],"support":[121],"algorithm.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"our":[129,146],"achieves":[131],"up":[132],"<tex":[134,150,154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135,151,155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.26\\times$</tex>":[136],"reduction":[137],"storage":[140],"with":[141],"acceptable":[142],"accuracy":[143],"degradation.":[144],"Additionally,":[145],"implementation":[148],"exhibits":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$839.72\\times$</tex>":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$5.72\\times$</tex>":[156],"speedup":[157],"comparison":[159],"CPU":[161],"GPU":[163],"implementations.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}