{"id":"https://openalex.org/W7106126674","doi":"https://doi.org/10.1109/iccad66269.2025.11240736","title":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","display_name":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7106126674","doi":"https://doi.org/10.1109/iccad66269.2025.11240736"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-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":null,"display_name":"Zhixiong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Zhixiong Zhao","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haomin Li","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":"Haomin Li","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fangxin Liu","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":"Fangxin Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuncheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuncheng Lu","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zongwu Wang","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":"Zongwu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Jiang","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":"Li Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haibing Guan","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":"Haibing Guan","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57481642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6159999966621399,"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":0.6159999966621399,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0608999989926815,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.0340999998152256,"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/speedup","display_name":"Speedup","score":0.7001000046730042},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6498000025749207},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5695000290870667},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5127999782562256},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47600001096725464},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008000016212463},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7001000046730042},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5695000290870667},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3125},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C115527620","wikidata":"https://www.wikidata.org/wiki/Q769909","display_name":"Nonlinear programming","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2914968962","https://openalex.org/W2923014074","https://openalex.org/W2953212265","https://openalex.org/W2998183051","https://openalex.org/W3017024317","https://openalex.org/W3138516171","https://openalex.org/W3159727696","https://openalex.org/W3173567919","https://openalex.org/W3189877953","https://openalex.org/W3196923642","https://openalex.org/W3202028501","https://openalex.org/W3204021316","https://openalex.org/W3207366647","https://openalex.org/W3211525823","https://openalex.org/W4252543992","https://openalex.org/W4285601701","https://openalex.org/W4293025109","https://openalex.org/W4293025835","https://openalex.org/W4308479898","https://openalex.org/W4312453883","https://openalex.org/W4313069943","https://openalex.org/W4387789586","https://openalex.org/W4389166736","https://openalex.org/W4390873361","https://openalex.org/W4390873673","https://openalex.org/W4393141090","https://openalex.org/W4393406920","https://openalex.org/W4400811165","https://openalex.org/W4403864152","https://openalex.org/W4404134117"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0,72],"models":[1,25],"have":[2],"revolutionized":[3],"computer":[4],"vision":[5],"(CV)":[6],"and":[7],"natural":[8],"language":[9],"processing":[10],"(NLP)":[11],"by":[12,123],"achieving":[13,74,104],"state-of-the-art":[14],"performance":[15],"across":[16],"a":[17,44,78,107],"range":[18],"of":[19,97,120],"benchmarks.":[20],"However,":[21],"nonlinear":[22,54,69,98,121],"operations":[23,55,70],"in":[24,53,100],"significantly":[26,92],"contribute":[27],"to":[28,56,83,106,128],"inference":[29],"latency,":[30],"presenting":[31],"unique":[32],"challenges":[33],"for":[34],"efficient":[35,58],"hardware":[36,63,118],"acceleration.":[37],"To":[38],"this":[39],"end,":[40],"we":[41],"propose":[42],"QUARK,":[43],"quantization-enabled":[45],"FPGA":[46],"acceleration":[47],"framework":[48],"that":[49,90],"leverages":[50],"common":[51],"patterns":[52],"enable":[57],"circuit":[59],"sharing,":[60],"thereby":[61],"reducing":[62],"resource":[64],"requirements.":[65],"QUARK":[66,91,115],"targets":[67],"all":[68,131],"within":[71],"models,":[73],"high-performance":[75],"approximation":[76],"through":[77],"novel":[79],"circuit-sharing":[80],"design":[81],"tailored":[82],"accelerate":[84],"these":[85],"operations.":[86],"Our":[87],"evaluation":[88],"demonstrates":[89],"reduces":[93],"the":[94,117],"computational":[95],"overhead":[96,119],"operators":[99],"mainstream":[101],"Transformer":[102],"architectures,":[103],"up":[105],"1.96\u00d7":[108],"end-to-end":[109],"speedup":[110],"over":[111],"GPU":[112],"implementations.":[113],"Moreover,":[114],"lowers":[116],"modules":[122],"more":[124],"than":[125],"50%":[126],"compared":[127],"prior":[129],"approaches,":[130],"while":[132],"maintaining":[133],"high":[134],"model":[135],"accuracy\u2014and":[136],"even":[137],"substantially":[138],"boosting":[139],"accuracy":[140],"under":[141],"ultra-low-bit":[142],"quantization.":[143]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-20T00:00:00"}
