{"id":"https://openalex.org/W4414197546","doi":"https://doi.org/10.1109/dac63849.2025.11133246","title":"BLOOM: Bit-Slice Framework for DNN Acceleration with Mixed-Precision","display_name":"BLOOM: Bit-Slice Framework for DNN Acceleration with Mixed-Precision","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197546","doi":"https://doi.org/10.1109/dac63849.2025.11133246"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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":"https://openalex.org/A5017670541","display_name":"Fangxin Liu","orcid":"https://orcid.org/0000-0002-8769-293X"},"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":true,"raw_author_name":"Fangxin Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030493839","display_name":"Ning Yang","orcid":"https://orcid.org/0009-0004-6964-8910"},"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":"Ning Yang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107269495","display_name":"Zongwu Wang","orcid":"https://orcid.org/0009-0003-2157-4927"},"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"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062059596","display_name":"Xuanpeng Zhu","orcid":"https://orcid.org/0009-0000-4859-9604"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]},{"id":"https://openalex.org/I4391767749","display_name":"State Key Laboratory of Mobile Networks and Mobile Multimedia Technology","ror":"https://ror.org/05cd55294","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanpeng Zhu","raw_affiliation_strings":["ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066348053","display_name":"Haidong Yao","orcid":"https://orcid.org/0009-0000-6911-9796"},"institutions":[{"id":"https://openalex.org/I4391767749","display_name":"State Key Laboratory of Mobile Networks and Mobile Multimedia Technology","ror":"https://ror.org/05cd55294","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]},{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haidong Yao","raw_affiliation_strings":["ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112620081","display_name":"Xiankui Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]},{"id":"https://openalex.org/I4391767749","display_name":"State Key Laboratory of Mobile Networks and Mobile Multimedia Technology","ror":"https://ror.org/05cd55294","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiankui Xiong","raw_affiliation_strings":["ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210098582","https://openalex.org/I4391767749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050285","display_name":"Jiang Li","orcid":"https://orcid.org/0009-0008-0549-7438"},"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"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049487451","display_name":"Haibing Guan","orcid":"https://orcid.org/0000-0002-4714-7400"},"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"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5017670541"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30608974,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11216","display_name":"Radiation Detection and Scintillator Technologies","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11216","display_name":"Radiation Detection and Scintillator Technologies","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11949","display_name":"Nuclear Physics and Applications","score":0.9706000089645386,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10597","display_name":"Nuclear reactor physics and engineering","score":0.92330002784729,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.6923999786376953},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6705999970436096},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.6686999797821045},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6432999968528748},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5799999833106995},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5332000255584717},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5317000150680542},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.44279998540878296},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4052000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230000138282776},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6923999786376953},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5799999833106995},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483000099658966},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2657631929","https://openalex.org/W2725159389","https://openalex.org/W2883920103","https://openalex.org/W2945146780","https://openalex.org/W2982479999","https://openalex.org/W2997375145","https://openalex.org/W3043504674","https://openalex.org/W3092209569","https://openalex.org/W3100985894","https://openalex.org/W3158020960","https://openalex.org/W3204021316","https://openalex.org/W4200036488","https://openalex.org/W4293023369","https://openalex.org/W4293023439","https://openalex.org/W4308083739","https://openalex.org/W4366341968","https://openalex.org/W4385245566","https://openalex.org/W4393406920","https://openalex.org/W4404057219","https://openalex.org/W4404134117"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4,86],"revolutionized":[5],"numerous":[6],"AI":[7],"applications,":[8],"but":[9],"their":[10],"vast":[11],"model":[12,208],"sizes":[13],"and":[14,35,91,119,138,198],"limited":[15],"hardware":[16,36],"resources":[17],"present":[18],"significant":[19],"deployment":[20],"challenges.":[21],"Model":[22],"quantization":[23,40,69],"offers":[24],"a":[25,115,120,180],"promising":[26],"solution":[27],"to":[28,102],"bridge":[29],"the":[30,57,65,94,128,131,172,176,182,186],"gap":[31],"between":[32],"DNN":[33],"size":[34],"capacity.":[37],"While":[38],"INT8":[39],"has":[41,47],"been":[42],"widely":[43],"used,":[44],"recent":[45],"research":[46],"pushed":[48],"for":[49],"even":[50],"lower":[51,163],"precision,":[52,155],"such":[53],"as":[54],"INT4.":[55],"However,":[56],"presence":[58],"of":[59,67,130,148],"outliers-values":[60],"with":[61,141],"unusually":[62],"large":[63],"magnitudes-limits":[64],"effectiveness":[66],"current":[68],"techniques.":[70,144],"Previous":[71],"compression-based":[72],"acceleration":[73],"methods":[74],"that":[75,89,151],"incorporate":[76],"outlieraware":[77],"encoding":[78],"introduce":[79,114],"complex":[80],"logic.":[81],"A":[82],"critical":[83],"issue":[84],"we":[85,113,169],"identified":[87],"is":[88,150],"serialization":[90],"deserialization":[92],"dominate":[93],"encoding/decoding":[95],"time":[96],"in":[97,175],"these":[98],"compression":[99],"workflows,":[100],"leading":[101],"substantial":[103],"performance":[104],"penalties":[105],"during":[106],"workflow":[107],"execution.":[108],"To":[109],"address":[110],"this":[111],"challenge,":[112],"novel":[116],"computing":[117],"approach":[118],"compatible":[121],"architecture":[122],"design":[123],"named":[124],"\u201cBLOOM\u201d.":[125],"BLOOM":[126,149],"leverages":[127],"strengths":[129],"\u201cbit-slicing\u201d":[132],"method,":[133],"effectively":[134],"combining":[135],"structured":[136],"mixed-precision":[137],"bit-level":[139],"sparsity":[140,174],"adaptive":[142],"dataflow":[143],"The":[145],"key":[146],"insight":[147],"outliers":[152],"require":[153],"higher":[154],"while":[156],"normal":[157],"values":[158],"can":[159],"be":[160],"processed":[161],"at":[162],"precision.":[164],"By":[165],"interleaving":[166],"4-bit":[167],"values,":[168],"efficiently":[170],"exploit":[171],"inherent":[173],"highprecision":[177],"components.":[178],"As":[179],"result,":[181],"BLOOM-based":[183],"accelerator":[184],"outperforms":[185],"existing":[187],"outlier-aware":[188],"accelerators":[189],"by":[190],"an":[191],"average":[192],"$1.2":[193],"\\sim":[194,201],"4.0":[195],"\\times$":[196],"speedup":[197],"$24.6":[199],"\\%":[200],"71.3":[202],"\\%$":[203],"energy":[204],"reduction,":[205],"respectively,":[206],"without":[207],"accuracy":[209],"loss.":[210]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}