{"id":"https://openalex.org/W3176468986","doi":"https://doi.org/10.1145/3453688.3461739","title":"Accommodating Transformer onto FPGA","display_name":"Accommodating Transformer onto FPGA","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3176468986","doi":"https://doi.org/10.1145/3453688.3461739","mag":"3176468986"},"language":"en","primary_location":{"id":"doi:10.1145/3453688.3461739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453688.3461739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Great Lakes Symposium on VLSI","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/A5077907495","display_name":"Panjie Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panjie Qi","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041623482","display_name":"Yuhong Song","orcid":"https://orcid.org/0000-0002-4310-2766"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Song","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwu Peng","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoyi Huang","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005358696","display_name":"Qingfeng Zhuge","orcid":"https://orcid.org/0000-0002-1107-3470"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Zhuge","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077381252","display_name":"Edwin H.\u2010M. Sha","orcid":"https://orcid.org/0000-0001-5605-5631"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Edwin Hsing-Mean Sha","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9962000250816345,"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":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8394337892532349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259427547454834},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6441218852996826},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.585226833820343},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5770687460899353},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49459215998649597},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.46588483452796936},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.44415953755378723},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42114168405532837},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41134387254714966},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3670436143875122},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3401957154273987},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3349558115005493},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17708894610404968}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8394337892532349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259427547454834},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6441218852996826},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.585226833820343},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5770687460899353},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49459215998649597},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.46588483452796936},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.44415953755378723},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42114168405532837},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41134387254714966},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3670436143875122},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3401957154273987},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3349558115005493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17708894610404968},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3453688.3461739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453688.3461739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Great Lakes Symposium on VLSI","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":17,"referenced_works":["https://openalex.org/W2009654791","https://openalex.org/W2751366252","https://openalex.org/W2895195713","https://openalex.org/W2911884654","https://openalex.org/W2917450576","https://openalex.org/W2962953210","https://openalex.org/W2963396654","https://openalex.org/W2963403868","https://openalex.org/W2964045208","https://openalex.org/W3016142271","https://openalex.org/W3025085339","https://openalex.org/W3047848469","https://openalex.org/W3092611151","https://openalex.org/W3104393472","https://openalex.org/W3104401858","https://openalex.org/W3121413886","https://openalex.org/W4234212765"],"related_works":["https://openalex.org/W4221139464","https://openalex.org/W4289827464","https://openalex.org/W2532502681","https://openalex.org/W4396520111","https://openalex.org/W2929170389","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4300097863","https://openalex.org/W4388913998","https://openalex.org/W4310584535"],"abstract_inverted_index":{"Recently,":[0],"Transformers":[1,16],"gradually":[2],"gain":[3],"popularity":[4],"and":[5,21,67,85,100,153,165,174],"perform":[6,148],"outstanding":[7],"for":[8,45,108,125],"many":[9],"Natural":[10],"Language":[11],"Processing":[12],"(NLP)":[13],"tasks.":[14],"However,":[15,48],"suffer":[17],"from":[18],"heavy":[19],"computation":[20],"memory":[22],"footprint,":[23],"making":[24],"it":[25],"difficult":[26],"to":[27,40,56,58,136,169],"deploy":[28],"on":[29,172],"embedded":[30],"devices.":[31],"The":[32],"field-programmable":[33],"gate":[34],"array":[35],"(FPGA)":[36],"is":[37],"widely":[38],"used":[39],"accelerate":[41],"deep":[42],"learning":[43],"algorithms":[44],"its":[46],"advantages.":[47],"the":[49,77,82,89,118,138],"trained":[50],"Transformer":[51,64],"models":[52],"are":[53],"too":[54],"large":[55],"accommodate":[57,63],"an":[59,73,102,123],"FPGA":[60,66],"fabric.":[61],"To":[62],"onto":[65],"achieve":[68,163],"efficient":[69,103],"execution,":[70],"we":[71,95,121,129],"propose":[72,101],"acceleration":[74],"framework":[75],"coupling":[76],"balanced":[78],"model":[79,135],"compression":[80],"at":[81,88],"algorithm":[83,93],"level":[84],"FPGA-implementation":[86],"optimization":[87],"hardware":[90,119],"level.":[91],"At":[92,117],"level,":[94,120],"adopt":[96],"a":[97,132],"block-balanced":[98],"pruning":[99,110],"sparse":[104,126],"matrix":[105],"storage":[106,157],"format":[107,147],"this":[109],"technique,":[111],"named":[112],"Compressed":[113],"Block":[114],"Row":[115],"(CBR).":[116],"design":[122],"accelerator":[124,161],"model.":[127],"And":[128,159],"also":[130],"abstract":[131],"performance":[133,139],"analytic":[134],"evaluate":[137],"of":[140],"accelerator.":[141],"Experiments":[142],"show":[143],"that":[144],"our":[145,160],"CBR":[146],"better":[149],"than":[150],"general":[151],"formats":[152],"can":[154,162],"significantly":[155],"save":[156],"space.":[158],"$38\\times$":[164],"$1.93\\times$":[166],"speedup":[167],"compared":[168],"other":[170],"works":[171],"CPU":[173],"GPU":[175],"respectively.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}