{"id":"https://openalex.org/W4396949147","doi":"https://doi.org/10.1109/isqed60706.2024.10528758","title":"A SIMD Dynamic Fixed Point Processing Engine for DNN Accelerators","display_name":"A SIMD Dynamic Fixed Point Processing Engine for DNN Accelerators","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4396949147","doi":"https://doi.org/10.1109/isqed60706.2024.10528758"},"language":"en","primary_location":{"id":"doi:10.1109/isqed60706.2024.10528758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed60706.2024.10528758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 25th International Symposium on Quality Electronic Design (ISQED)","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/A5028707436","display_name":"Gopal Raut","orcid":"https://orcid.org/0000-0002-1046-9457"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gopal Raut","raw_affiliation_strings":["Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066835728","display_name":"Pranose J. Edavoor","orcid":"https://orcid.org/0000-0002-2133-7126"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranose J Edavoor","raw_affiliation_strings":["Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091068830","display_name":"David Selvakumar","orcid":"https://orcid.org/0000-0002-7461-1416"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"David Selvakumar","raw_affiliation_strings":["Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112043973","display_name":"Ritambhara Thakur","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ritambhara Thakur","raw_affiliation_strings":["Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Secure Hardware and VLSI Design Group, Centre for Development of Advanced Computing,Bangalore,India","institution_ids":["https://openalex.org/I1331500379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028707436"],"corresponding_institution_ids":["https://openalex.org/I1331500379"],"apc_list":null,"apc_paid":null,"fwci":2.5928,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90441552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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/T11044","display_name":"Particle Detector Development and Performance","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7728292942047119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442445158958435},{"id":"https://openalex.org/keywords/fixed-point","display_name":"Fixed point","score":0.5501695871353149},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5472748279571533},{"id":"https://openalex.org/keywords/fixed-point-arithmetic","display_name":"Fixed-point arithmetic","score":0.5220125317573547},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43794605135917664},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.21239840984344482},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17467379570007324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06619229912757874}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7728292942047119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442445158958435},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.5501695871353149},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5472748279571533},{"id":"https://openalex.org/C163973906","wikidata":"https://www.wikidata.org/wiki/Q649900","display_name":"Fixed-point arithmetic","level":3,"score":0.5220125317573547},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43794605135917664},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.21239840984344482},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17467379570007324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06619229912757874},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isqed60706.2024.10528758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed60706.2024.10528758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 25th International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2150633168","https://openalex.org/W2271840356","https://openalex.org/W2563468918","https://openalex.org/W2607445385","https://openalex.org/W2890165800","https://openalex.org/W2895531329","https://openalex.org/W2897295818","https://openalex.org/W2949275038","https://openalex.org/W2971946864","https://openalex.org/W2978565318","https://openalex.org/W2982041622","https://openalex.org/W3047364742","https://openalex.org/W3090369187","https://openalex.org/W3090444025","https://openalex.org/W3103169341","https://openalex.org/W3124625166","https://openalex.org/W3184606595","https://openalex.org/W3211454547","https://openalex.org/W4212886211","https://openalex.org/W4283791586","https://openalex.org/W4285055485","https://openalex.org/W4362683530","https://openalex.org/W4375861680","https://openalex.org/W4378765272","https://openalex.org/W4379115821","https://openalex.org/W6694517276","https://openalex.org/W6853492412"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2162726111","https://openalex.org/W2022397046","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W2117755361","https://openalex.org/W2286348849","https://openalex.org/W2018511057","https://openalex.org/W2478126787","https://openalex.org/W1587248296"],"abstract_inverted_index":{"This":[0,45,161],"research":[1],"introduces":[2],"a":[3,38,125,144,157,193],"novel":[4],"Processing":[5],"Engine":[6],"(PE)":[7],"for":[8,82,102,107,113,131,151,166,203],"convolution":[9],"layers":[10,191],"in":[11,88,128,156],"Deep":[12],"Neural":[13],"Network":[14],"(DNN)":[15],"accelerators.":[16],"The":[17,92],"PE":[18,196],"integrates":[19],"multi-precision":[20,58,83,162],"dynamic":[21,49,64,84,204],"fraction":[22,65,85,205],"fixed-point":[23,66,86],"Multiply-Accumulate":[24],"(MAC)":[25],"and":[26,54,72,111,134,137,147,153,170,180,190,200],"Activation":[27],"Function":[28],"(AF)":[29],"units":[30,202],"(8/16":[31],"bits":[32,155],"with":[33,63,104,109,115,197],"shared":[34],"resources),":[35],"functioning":[36],"as":[37],"Single":[39],"Instruction,":[40],"Multiple":[41],"Data":[42],"(SIMD)":[43],"engine.":[44],"innovative":[46],"design":[47,150],"enables":[48],"precision":[50],"switching":[51],"between":[52],"8-bit":[53],"16-bit":[55,173],"computations,":[56],"supporting":[57],"(N=8":[59],"or":[60],"16)":[61],"operations":[62],"data.":[67],"Pareto":[68],"analysis":[69],"optimizes":[70,175],"resources":[71,130,165],"determines":[73],"the":[74,89],"ideal":[75],"number":[76],"of":[77],"parallel":[78],"Cordic":[79],"stages":[80],"required":[81],"AF":[87,148,201],"SIMD":[90,158],"Engine.":[91],"proposed":[93],"approach":[94],"demonstrates":[95],"minimal":[96],"accuracy":[97],"loss,":[98],"less":[99],"than":[100],"1%":[101,106],"LeNet":[103],"MNIST,":[105],"AlexNet":[108],"CIFAR-10,":[110,116],"2%":[112],"VGG16":[114],"compared":[117],"to":[118],"reference":[119],"float32-based":[120],"implementations.":[121],"Experimental":[122],"results":[123],"show":[124],"significant":[126],"reduction":[127],"hardware":[129],"MAC":[132,146,199],"unit":[133,149],"AF,":[135],"51.83%":[136],"43.50%,":[138],"respectively,":[139],"indicating":[140],"substantial":[141],"improvements":[142],"over":[143],"separate":[145],"8":[152,169],"16":[154],"engine-based":[159],"setup.":[160],"design,":[163],"sharing":[164],"4":[167],"$\\times$":[168,172],"1":[171],"processing,":[174],"resource":[176],"utilization,":[177],"boosts":[178],"versatility":[179],"throughput,":[181],"enabling":[182],"efficient":[183],"computations":[184],"across":[185],"diverse":[186],"DNN":[187],"applications,":[188],"models,":[189],"using":[192],"unique":[194],"SIMD-enabled":[195],"integrated":[198],"fixedpoint":[206],"operations.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}