{"id":"https://openalex.org/W3115004860","doi":"https://doi.org/10.1109/hpec43674.2020.9286170","title":"Variable Precision Multiplication for Software-Based Neural Networks","display_name":"Variable Precision Multiplication for Software-Based Neural Networks","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3115004860","doi":"https://doi.org/10.1109/hpec43674.2020.9286170","mag":"3115004860"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5101477777","display_name":"Richa Singh","orcid":"https://orcid.org/0000-0002-3802-0061"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richa Singh","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084106379","display_name":"Thomas B. Conroy","orcid":"https://orcid.org/0000-0003-4930-2248"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Conroy","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088000939","display_name":"Patrick Schaumont","orcid":"https://orcid.org/0000-0002-4586-5476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Schaumont","raw_affiliation_strings":["WPI"],"affiliations":[{"raw_affiliation_string":"WPI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101477777"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.1552,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78339141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9948999881744385,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9944999814033508,"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":0.8318221569061279},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6493641138076782},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5683437585830688},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.522167444229126},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5080852508544922},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5043295621871948},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4909854233264923},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47244197130203247},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.44925177097320557},{"id":"https://openalex.org/keywords/multiplier","display_name":"Multiplier (economics)","score":0.4457700848579407},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4456188380718231},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42921558022499084},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40473902225494385},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3470868170261383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23275470733642578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318221569061279},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6493641138076782},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5683437585830688},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.522167444229126},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5080852508544922},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5043295621871948},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4909854233264923},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47244197130203247},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.44925177097320557},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.4457700848579407},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4456188380718231},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42921558022499084},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40473902225494385},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3470868170261383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23275470733642578},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5913383716","display_name":null,"funder_award_id":"1931639","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W194100104","https://openalex.org/W1548516269","https://openalex.org/W2048266589","https://openalex.org/W2300242332","https://openalex.org/W2472766990","https://openalex.org/W2483966489","https://openalex.org/W2602892162","https://openalex.org/W2613550625","https://openalex.org/W2898271894","https://openalex.org/W2951978180","https://openalex.org/W2955723980","https://openalex.org/W2979730268","https://openalex.org/W3013186616","https://openalex.org/W3022798397","https://openalex.org/W3099393250","https://openalex.org/W3170113470","https://openalex.org/W6720403304","https://openalex.org/W6736049462","https://openalex.org/W6755776133"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3102660566","https://openalex.org/W4296617584","https://openalex.org/W2588463123","https://openalex.org/W2550374317","https://openalex.org/W4302004660"],"abstract_inverted_index":{"As":[0],"the":[1,13,39,83,137,174],"number":[2],"of":[3,5,42,61,108,163,207],"applications":[4],"neural":[6,33,44,133,171],"networks":[7,34,45],"continues":[8],"to":[9,15,31,91,154,170,185],"grow,":[10],"so":[11],"does":[12],"need":[14],"efficiently":[16,92],"perform":[17],"inference":[18,189],"computations":[19],"on":[20,125,158],"highly":[21],"constrained":[22],"devices.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,122],"propose":[28],"a":[29,51,72,118,132,178,205],"methodology":[30],"accelerate":[32],"in":[35,50,96,143,194],"software.":[36],"We":[37,86,103],"exploit":[38],"limited-precision":[40,73],"requirements":[41],"typical":[43],"by":[46,98,204],"formulating":[47],"recurring":[48],"operations":[49],"bit-slice":[52],"computation":[53,56],"format.":[54],"Bit-slice":[55],"ensures":[57],"that":[58,166],"every":[59],"bit":[60],"an":[62,89],"M-bit":[63],"processor":[64],"word":[65],"contributes":[66],"useful":[67],"work":[68],"even":[69],"while":[70],"computing":[71],"n-bit":[74],"(with":[75],"n":[76],"<;":[77],"M)":[78],"operation.":[79],"This":[80],"paper":[81],"brings":[82],"following":[84],"contributions.":[85],"first":[87],"present":[88],"environment":[90],"create":[93],"bitslice":[94],"descriptions":[95],"software,":[97],"synthesizing":[99],"them":[100],"from":[101],"Verilog.":[102],"then":[104],"develop":[105],"bitsliced":[106],"designs":[107],"matrix":[109,199],"multiplication":[110],"and":[111,121,152,187],"evaluate":[112],"their":[113],"performance.":[114],"Our":[115,128],"target":[116],"is":[117,131],"small":[119],"microcontroller,":[120],"rely":[123],"solely":[124],"software":[126],"optimization.":[127],"driving":[129],"application":[130],"network":[134,172],"classifier":[135],"for":[136,167],"MNIST":[138],"database.":[139],"Range-Based":[140],"Linear":[141],"Quantization":[142],"symmetric":[144],"mode":[145],"quantizes":[146],"pre-trained":[147],"32-bit":[148],"floating":[149],"point":[150],"weights":[151],"activation":[153],"low-precision":[155],"data-widths.":[156],"Experiments":[157],"RISC-V":[159],"with":[160,211,216],"varying":[161],"levels":[162],"hardware-support":[164],"show":[165],"data-widths":[168],"common":[169],"applications,":[173],"bit-sliced":[175],"code":[176],"produces":[177],"speedup":[179],"over":[180],"traditional":[181],"methods,":[182],"which":[183],"leads":[184],"faster":[186],"efficient":[188],"without":[190],"incurring":[191],"significant":[192],"loss":[193],"accuracy.":[195],"For":[196],"example,":[197],"8-bit":[198],"multiplications":[200],"are":[201],"sped":[202],"up":[203],"factor":[206],"2.62\u00d7":[208],"when":[209],"compared":[210],"non-bitsliced":[212],"rv32i":[213],"ISA":[214],"implementation":[215],"no":[217],"hardware":[218],"multiplier.":[219]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}