{"id":"https://openalex.org/W3108338285","doi":"https://doi.org/10.1145/3492733","title":"Ax-BxP: Approximate Blocked Computation for Precision-reconfigurable Deep Neural Network Acceleration","display_name":"Ax-BxP: Approximate Blocked Computation for Precision-reconfigurable Deep Neural Network Acceleration","publication_year":2022,"publication_date":"2022-01-28","ids":{"openalex":"https://openalex.org/W3108338285","doi":"https://doi.org/10.1145/3492733","mag":"3108338285"},"language":"en","primary_location":{"id":"doi:10.1145/3492733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492733","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3492733","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034434035","display_name":"R. Elangovan","orcid":"https://orcid.org/0000-0001-9646-5088"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reena Elangovan","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-9646-5088","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086674756","display_name":"Shubham Jain","orcid":"https://orcid.org/0000-0002-2291-7712"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Jain","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2291-7712","affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-4624-564X","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5873,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64113187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"27","issue":"3","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9994000196456909,"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":0.8305121064186096},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.77300626039505},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.7546002268791199},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6102887988090515},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5630537271499634},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5360261797904968},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48087528347969055},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4567715525627136},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4566556215286255},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4495205283164978},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.43975040316581726},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.416806161403656},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3898792862892151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1816336214542389},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.17873555421829224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08942469954490662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305121064186096},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.77300626039505},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7546002268791199},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6102887988090515},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5630537271499634},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5360261797904968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48087528347969055},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4567715525627136},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4566556215286255},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4495205283164978},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.43975040316581726},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.416806161403656},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3898792862892151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1816336214542389},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.17873555421829224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08942469954490662},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3492733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492733","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3492733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492733","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3108338285.pdf","grobid_xml":"https://content.openalex.org/works/W3108338285.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1910331302","https://openalex.org/W1982970530","https://openalex.org/W1991735330","https://openalex.org/W1996431812","https://openalex.org/W1998917233","https://openalex.org/W1999890536","https://openalex.org/W2034581485","https://openalex.org/W2040056309","https://openalex.org/W2051831389","https://openalex.org/W2065359960","https://openalex.org/W2073123623","https://openalex.org/W2104578404","https://openalex.org/W2106484393","https://openalex.org/W2121819644","https://openalex.org/W2126044301","https://openalex.org/W2150100620","https://openalex.org/W2151608824","https://openalex.org/W2155458498","https://openalex.org/W2159211021","https://openalex.org/W2171661253","https://openalex.org/W2293587938","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2323130283","https://openalex.org/W2330958039","https://openalex.org/W2405920868","https://openalex.org/W2464177207","https://openalex.org/W2469490737","https://openalex.org/W2472587927","https://openalex.org/W2524428287","https://openalex.org/W2560114385","https://openalex.org/W2563587242","https://openalex.org/W2563860341","https://openalex.org/W2604319603","https://openalex.org/W2606722458","https://openalex.org/W2653504903","https://openalex.org/W2719597717","https://openalex.org/W2751477244","https://openalex.org/W2786771851","https://openalex.org/W2809371234","https://openalex.org/W2810704618","https://openalex.org/W2871705258","https://openalex.org/W2900327659","https://openalex.org/W2913668833","https://openalex.org/W2945652047","https://openalex.org/W2953212265","https://openalex.org/W2955425717","https://openalex.org/W2963367920","https://openalex.org/W2964299589","https://openalex.org/W2982479999","https://openalex.org/W2987956272","https://openalex.org/W3001665736","https://openalex.org/W3030163527"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2146872326","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Precision":[0],"scaling":[1],"has":[2],"emerged":[3],"as":[4,71],"a":[5,37,50,55,87,103,121,137,147,151,197,205],"popular":[6],"technique":[7],"to":[8,35,54,57,128,149],"optimize":[9],"the":[10,31,79,110,124,160,193],"compute":[11],"and":[12,45,145,163,172,202,213],"storage":[13],"requirements":[14],"of":[15,81,105,112,123],"Deep":[16],"Neural":[17],"Networks":[18],"(DNNs).":[19],"Efforts":[20],"toward":[21],"creating":[22],"ultra-low-precision":[23],"(sub-8-bit)":[24],"DNNs":[25],"for":[26,67,89,155],"efficient":[27],"inference":[28],"suggest":[29],"that":[30,140],"minimum":[32],"precision":[33,60,130],"required":[34,125],"achieve":[36,208],"given":[38,157],"network-level":[39],"accuracy":[40],"varies":[41],"considerably":[42],"across":[43,47,200],"networks,":[44],"even":[46],"layers":[48,201],"within":[49,204],"network.":[51],"This":[52],"translates":[53],"need":[56],"support":[58],"variable":[59],"computation":[61,92,144],"in":[62,169,187,210],"DNN":[63,138],"hardware.":[64],"Previous":[65],"proposals":[66],"precision-reconfigurable":[68],"hardware,":[69],"such":[70],"bit-serial":[72],"architectures,":[73],"incur":[74],"high":[75,133],"overheads,":[76],"significantly":[77],"diminishing":[78],"benefits":[80],"lower":[82],"precision.":[83],"We":[84,135],"propose":[85,146],"Ax-BxP,":[86],"method":[88,148],"approximate":[90,142],"blocked":[91,143],"wherein":[93],"each":[94],"multiply-accumulate":[95],"operation":[96],"is":[97,102],"performed":[98],"block-wise":[99,126],"(a":[100],"block":[101],"group":[104],"bits),":[106],"facilitating":[107],"re-configurability":[108,131],"at":[109,196],"granularity":[111,199],"blocks.":[113],"Further,":[114,190],"approximations":[115],"are":[116],"introduced":[117],"by":[118,191],"only":[119],"performing":[120],"subset":[122],"computations":[127],"realize":[129],"with":[132,181],"efficiency.":[134],"design":[136],"accelerator":[139],"embodies":[141],"determine":[150],"suitable":[152],"approximation":[153,194],"configuration":[154],"any":[156],"DNN.":[158],"For":[159],"AlexNet,":[161],"ResNet50,":[162],"MobileNetV2":[164],"DNNs,":[165],"Ax-BxP":[166],"achieves":[167],"improvement":[168,209],"system":[170,211],"energy":[171,212],"performance,":[173,214],"respectively,":[174],"over":[175],"an":[176],"8-bit":[177],"fixed-point":[178],"(FxP8)":[179],"baseline,":[180],"minimal":[182],"loss":[183],"(<1%":[184],"on":[185],"average)":[186],"classification":[188],"accuracy.":[189],"varying":[192],"configurations":[195],"finer":[198],"data-structures":[203],"DNN,":[206],"we":[207],"respectively.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}