{"id":"https://openalex.org/W7116367094","doi":"https://doi.org/10.1145/3754598.3754660","title":"SmartBlock: Adaptive Block Floating Point Quantization for Efficient DNN Acceleration","display_name":"SmartBlock: Adaptive Block Floating Point Quantization for Efficient DNN Acceleration","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116367094","doi":"https://doi.org/10.1145/3754598.3754660"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754660","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Ju","orcid":"https://orcid.org/0009-0006-0875-196X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Ju","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-0875-196X","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104105363","display_name":"Jingkui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkui Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-1462-0397","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5875-3297","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120871951","display_name":"Jun He","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun He","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0003-9830-2663","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Feng","orcid":"https://orcid.org/0009-0008-3854-5336"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Feng","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-3854-5336","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072361503","display_name":"Minjin Tang","orcid":"https://orcid.org/0009-0000-2254-4912"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjin Tang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0000-2254-4912","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120880580","display_name":"Zhaoyun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyun Chen","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1552-8396","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yang Shi","orcid":"https://orcid.org/0000-0001-5786-3171"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Shi","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5786-3171","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60375221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5651999711990356,"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":0.5651999711990356,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.08049999922513962,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.07039999961853027,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6746000051498413},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6478000283241272},{"id":"https://openalex.org/keywords/accumulator","display_name":"Accumulator (cryptography)","score":0.6464999914169312},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.6011999845504761},{"id":"https://openalex.org/keywords/hydraulic-accumulator","display_name":"Hydraulic accumulator","score":0.5509999990463257},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5238999724388123},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4438999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786999702453613},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6746000051498413},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C2078106","wikidata":"https://www.wikidata.org/wiki/Q14906620","display_name":"Accumulator (cryptography)","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C19221803","wikidata":"https://www.wikidata.org/wiki/Q4668679","display_name":"Hydraulic accumulator","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C87133666","wikidata":"https://www.wikidata.org/wiki/Q1161699","display_name":"Dynamic range","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.9029479622840881,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2606722458","https://openalex.org/W2883920103","https://openalex.org/W2923014074","https://openalex.org/W2945146780","https://openalex.org/W2963748441","https://openalex.org/W2989569745","https://openalex.org/W3043504674","https://openalex.org/W3130554079","https://openalex.org/W3208633927","https://openalex.org/W4308083739","https://openalex.org/W4313467202","https://openalex.org/W4383604851","https://openalex.org/W4389491858","https://openalex.org/W4393406935"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"as":[8,32],"model":[9,35,43],"sizes":[10],"continue":[11],"to":[12,89],"grow,":[13],"driving":[14],"the":[15,49,86,100,111,114,120],"need":[16],"for":[17],"optimizations":[18],"in":[19,66],"both":[20],"computational":[21],"and":[22,45,105],"energy":[23,67,122],"efficiency.":[24,68],"Block":[25],"Floating":[26],"Point":[27],"(BFP)":[28],"quantization":[29],"has":[30],"emerged":[31],"an":[33],"effective":[34],"compression":[36],"technique,":[37],"offering":[38],"a":[39,60,80,91],"favorable":[40],"trade-off":[41],"between":[42],"accuracy":[44],"hardware":[46],"cost.":[47],"However,":[48],"frequent":[50],"use":[51],"of":[52,85,94,102,113],"floating-point":[53],"(FP)":[54],"accumulation":[55],"across":[56],"BFP":[57],"blocks":[58],"remains":[59],"significant":[61],"bottleneck,":[62],"limiting":[63,119],"further":[64],"improvements":[65],"State-of-the-art":[69],"(SotA)":[70],"accelerators":[71],"mitigate":[72],"this":[73,97],"issue":[74],"by":[75],"introducing":[76],"low-overhead":[77],"accumulators":[78],"with":[79],"narrower":[81],"dynamic":[82],"range":[83,93],"ahead":[84],"FP":[87],"accumulator":[88],"handle":[90],"small":[92],"values.":[95],"While":[96],"approach":[98],"reduces":[99],"activation":[101],"power-hungry":[103],"alignment":[104],"format":[106],"conversion":[107],"units,":[108],"it":[109],"increases":[110],"complexity":[112],"processing":[115],"elements":[116],"(PEs),":[117],"thereby":[118],"overall":[121],"savings.":[123]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}