{"id":"https://openalex.org/W4388837988","doi":"https://doi.org/10.1109/tc.2023.3334140","title":"Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators","display_name":"Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388837988","doi":"https://doi.org/10.1109/tc.2023.3334140"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3334140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3334140","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.12224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076323022","display_name":"Trevor E. Pogue","orcid":"https://orcid.org/0000-0002-6791-3758"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Trevor E. Pogue","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6791-3758","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048457847","display_name":"Nicola Nicolici","orcid":"https://orcid.org/0000-0001-6345-5908"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nicola Nicolici","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6345-5908","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada","institution_ids":["https://openalex.org/I98251732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98251732"],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":0.4974,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.58921117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"73","issue":"2","first_page":"495","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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/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/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":0.7583879232406616},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7010269165039062},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.648106038570404},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.6131243705749512},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5956882238388062},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.588936448097229},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5643435120582581},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5005347728729248},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47596806287765503},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.45054471492767334},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.43062126636505127},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38936647772789},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22604015469551086},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.13468340039253235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13089343905448914},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.12380751967430115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583879232406616},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7010269165039062},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.648106038570404},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.6131243705749512},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5956882238388062},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.588936448097229},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5643435120582581},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5005347728729248},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47596806287765503},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.45054471492767334},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.43062126636505127},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38936647772789},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22604015469551086},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.13468340039253235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13089343905448914},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.12380751967430115},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2023.3334140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3334140","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2311.12224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.12224","pdf_url":"https://arxiv.org/pdf/2311.12224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.12224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.12224","pdf_url":"https://arxiv.org/pdf/2311.12224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388837988.pdf","grobid_xml":"https://content.openalex.org/works/W4388837988.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1497617500","https://openalex.org/W1993929164","https://openalex.org/W2052012422","https://openalex.org/W2066749436","https://openalex.org/W2080275298","https://openalex.org/W2114427352","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2885108132","https://openalex.org/W2896983500","https://openalex.org/W2902895686","https://openalex.org/W2935480346","https://openalex.org/W2953212265","https://openalex.org/W2963122961","https://openalex.org/W2977634443","https://openalex.org/W2997106510","https://openalex.org/W3000160544","https://openalex.org/W3127736057","https://openalex.org/W3129147932","https://openalex.org/W3132745255","https://openalex.org/W3178956316","https://openalex.org/W3193946904","https://openalex.org/W4226104804","https://openalex.org/W4226337850","https://openalex.org/W4297922476","https://openalex.org/W4315473892","https://openalex.org/W4360770687","https://openalex.org/W4380874786"],"related_works":["https://openalex.org/W2347854075","https://openalex.org/W2022229285","https://openalex.org/W46448156","https://openalex.org/W2078268640","https://openalex.org/W2283084692","https://openalex.org/W2130878144","https://openalex.org/W2150609674","https://openalex.org/W3172158163","https://openalex.org/W3028347934","https://openalex.org/W2132614232"],"abstract_inverted_index":{"We":[0,63,111],"introduce":[1],"a":[2,90,94,154],"new":[3],"algorithm":[4,22,78],"called":[5],"the":[6,30,67,104,128,133,143,178,183],"Free-pipeline":[7],"Fast":[8],"Inner":[9],"Product":[10],"(FFIP)":[11],"and":[12,60,79,106,109,174],"its":[13],"hardware":[14,96,156],"architecture":[15,81],"that":[16,49,113,148],"improve":[17,84],"an":[18,71],"under-explored":[19],"fast":[20],"inner-product":[21],"(FIP)":[23],"proposed":[24],"by":[25],"Winograd":[26,32],"in":[27,70],"1968.":[28],"Unlike":[29],"unrelated":[31],"minimal":[33],"filtering":[34],"algorithms":[35,108],"for":[36,66,93,103,161],"convolutional":[37],"layers,":[38],"FIP":[39,65,105],"is":[40],"applicable":[41],"to":[42,53,126,167],"all":[43],"machine":[44],"learning":[45],"(ML)":[46],"model":[47],"layers":[48],"can":[50,115,141,149],"mainly":[51],"decompose":[52],"matrix":[54],"multiplication,":[55],"including":[56],"fully-connected,":[57],"convolutional,":[58],"recurrent,":[59],"attention/transformer":[61],"layers.":[62],"implement":[64],"first":[68],"time":[69],"ML":[72,124,163],"accelerator":[73],"then":[74],"present":[75],"our":[76],"FFIP":[77,107,114,159],"generalized":[80],"which":[82],"inherently":[83],"FIP's":[85],"clock":[86],"frequency":[87],"and,":[88],"as":[89],"consequence,":[91],"throughput":[92,130,173],"similar":[95],"cost.":[97],"Finally,":[98],"we":[99],"contribute":[100],"ML-specific":[101],"optimizations":[102],"architectures.":[110],"show":[112],"be":[116],"seamlessly":[117],"incorporated":[118],"into":[119],"traditional":[120],"fixed-point":[121,169],"systolic":[122,145],"array":[123,146],"accelerators":[125],"achieve":[127],"same":[129,184],"with":[131,153,165],"half":[132],"number":[134],"of":[135,186],"multiply-accumulate":[136],"(MAC)":[137],"units,":[138],"or":[139],"it":[140],"double":[142],"maximum":[144],"size":[147],"fit":[150],"onto":[151],"devices":[152],"fixed":[155],"budget.":[157],"Our":[158],"implementation":[160],"non-sparse":[162],"models":[164],"8":[166],"16-bit":[168],"inputs":[170],"achieves":[171],"higher":[172],"compute":[175,187],"efficiency":[176],"than":[177],"best-in-class":[179],"prior":[180],"solutions":[181],"on":[182],"type":[185],"platform.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}