{"id":"https://openalex.org/W2997869757","doi":"https://doi.org/10.1109/tcsi.2019.2958568","title":"Optimizing Weight Mapping and Data Flow for Convolutional Neural Networks on Processing-in-Memory Architectures","display_name":"Optimizing Weight Mapping and Data Flow for Convolutional Neural Networks on Processing-in-Memory Architectures","publication_year":2019,"publication_date":"2019-12-25","ids":{"openalex":"https://openalex.org/W2997869757","doi":"https://doi.org/10.1109/tcsi.2019.2958568","mag":"2997869757"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2019.2958568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2019.2958568","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-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/A5076031530","display_name":"Xiaochen Peng","orcid":"https://orcid.org/0000-0001-6148-7711"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaochen Peng","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0001-6148-7711","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489436","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-1642-3473"},"institutions":[{"id":"https://openalex.org/I4210088951","display_name":"Synopsys (United States)","ror":"https://ror.org/013by2m91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088951"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Design Group of Synopsys, Mountain View, USA","School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Design Group of Synopsys, Mountain View, USA","institution_ids":["https://openalex.org/I4210088951"]},{"raw_affiliation_string":"School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054894631","display_name":"Shimeng Yu","orcid":"https://orcid.org/0000-0002-0068-3652"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shimeng Yu","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-0068-3652","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4877,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.96546354,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"67","issue":"4","first_page":"1333","last_page":"1343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025744557380676},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.654452919960022},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5894315838813782},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.5714936256408691},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5447670817375183},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5148831605911255},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4602450728416443},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45937904715538025},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45069557428359985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4477505683898926},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3563773036003113},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33303302526474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31813088059425354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2240649163722992},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1138843297958374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025744557380676},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.654452919960022},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5894315838813782},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.5714936256408691},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5447670817375183},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5148831605911255},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4602450728416443},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45937904715538025},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45069557428359985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4477505683898926},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3563773036003113},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33303302526474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31813088059425354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2240649163722992},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1138843297958374},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2019.2958568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2019.2958568","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2322102437","display_name":null,"funder_award_id":"2018-NC-2762","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G5466162600","display_name":null,"funder_award_id":"NSF-CCF-1740225","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8675392359","display_name":null,"funder_award_id":"NSF-CCF-1903951","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"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1946546377","https://openalex.org/W2048266589","https://openalex.org/W2057055374","https://openalex.org/W2117539524","https://openalex.org/W2168972302","https://openalex.org/W2194775991","https://openalex.org/W2267635276","https://openalex.org/W2300242332","https://openalex.org/W2433248078","https://openalex.org/W2508602506","https://openalex.org/W2510331918","https://openalex.org/W2518281301","https://openalex.org/W2593564159","https://openalex.org/W2594492285","https://openalex.org/W2606722458","https://openalex.org/W2608111952","https://openalex.org/W2613989746","https://openalex.org/W2741527259","https://openalex.org/W2782046614","https://openalex.org/W2785141883","https://openalex.org/W2787513570","https://openalex.org/W2794194363","https://openalex.org/W2798554798","https://openalex.org/W2921351161","https://openalex.org/W2922487710","https://openalex.org/W2943765373","https://openalex.org/W2963387357","https://openalex.org/W2964164125","https://openalex.org/W2999599167","https://openalex.org/W3023154643","https://openalex.org/W3024621361","https://openalex.org/W4295262505","https://openalex.org/W6637373629","https://openalex.org/W6664870454","https://openalex.org/W6684474170","https://openalex.org/W6693397755","https://openalex.org/W6698200048","https://openalex.org/W6734592959","https://openalex.org/W6748319235","https://openalex.org/W6750749591","https://openalex.org/W6767216769"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W3171253712","https://openalex.org/W1200423363","https://openalex.org/W2734796617","https://openalex.org/W2171591485","https://openalex.org/W2393236177","https://openalex.org/W3152874605"],"abstract_inverted_index":{"Recent":[0],"state-of-the-art":[1],"deep":[2],"convolutional":[3,72],"neural":[4],"networks":[5],"(CNNs)":[6],"have":[7,29],"shown":[8],"remarkable":[9],"success":[10],"in":[11,96,171,214],"current":[12],"intelligent":[13],"systems":[14],"for":[15,47,106,176],"various":[16],"tasks,":[17],"such":[18],"as":[19],"image/speech":[20],"recognition":[21],"and":[22,59,102,116,125,161,168,173,195,211,216,223],"classification.":[23],"A":[24],"number":[25],"of":[26,70,78],"recent":[27],"efforts":[28],"attempted":[30],"to":[31,88,98,135],"design":[32,151,182],"custom":[33],"inference":[34],"engines":[35],"based":[36,148,183],"on":[37,184],"processing-in-memory":[38],"(PIM)":[39],"architecture,":[40,108,202],"where":[41,83],"the":[42,53,71,84,117,123,127,180,185,192],"memory":[43,146],"array":[44],"is":[45,155],"used":[46],"weighted":[48],"sum":[49],"computation,":[50],"thereby":[51],"avoiding":[52],"frequent":[54],"data":[55,86,104,119,129,162],"transfer":[56],"between":[57],"buffers":[58],"computation":[60],"units.":[61],"Prior":[62],"PIM":[63,107,150],"designs":[64],"typically":[65],"unroll":[66],"each":[67],"3D":[68],"kernel":[69],"layers":[73],"into":[74,130],"a":[75,79,111,140],"vertical":[76],"column":[77],"large":[80],"weight":[81,101,113],"matrix,":[82],"input":[85,103,128],"needs":[87],"be":[89],"accessed":[90],"multiple":[91],"times.":[92],"In":[93],"this":[94],"paper,":[95],"order":[97],"maximize":[99],"both":[100],"reuse":[105],"we":[109,197],"propose":[110,198],"novel":[112],"mapping":[114,159,187],"method":[115,160],"corresponding":[118],"flow":[120,163],"which":[121,219],"divides":[122],"kernels":[124],"assign":[126],"different":[131],"processing-elements":[132],"(PEs)":[133],"according":[134],"their":[136],"spatial":[137],"locations.":[138],"As":[139],"case":[141],"study,":[142],"resistive":[143],"random":[144],"access":[145],"(RRAM)":[147],"8-bit":[149],"at":[152],"32":[153],"nm":[154],"benchmarked.":[156],"The":[157],"proposed":[158],"yields":[164],"~2.03\u00d7":[165],"speed":[166],"up":[167],"~1.4\u00d7":[169],"improvement":[170,213],"throughput":[172,215],"energy":[174,217],"efficiency":[175],"ResNet-34,":[177],"compared":[178],"with":[179,203],"prior":[181],"conventional":[186],"method.":[188],"To":[189],"further":[190],"optimize":[191],"hardware":[193],"performance":[194],"throughput,":[196],"an":[199],"optimal":[200],"pipeline":[201],"~50%":[204],"area":[205],"overhead,":[206],"it":[207],"achieves":[208],"overall":[209],"913\u00d7":[210],"1.96\u00d7":[212],"efficiency,":[218],"are":[220],"132476":[221],"FPS":[222],"20.1":[224],"TOPS/W,":[225],"respectively.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}