{"id":"https://openalex.org/W4389692499","doi":"https://doi.org/10.1109/tcad.2023.3342605","title":"NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators With 3-D Stacked-DRAM","display_name":"NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators With 3-D Stacked-DRAM","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4389692499","doi":"https://doi.org/10.1109/tcad.2023.3342605"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2023.3342605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3342605","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","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/A5100669438","display_name":"Junpeng Wang","orcid":"https://orcid.org/0000-0002-8810-3172"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junpeng Wang","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032602090","display_name":"Mengke Ge","orcid":"https://orcid.org/0000-0001-7888-9370"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengke Ge","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei, China","School of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066572489","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0001-5939-7346"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031010282","display_name":"Qi Xu","orcid":"https://orcid.org/0000-0002-0375-9800"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Xu","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423614","display_name":"Song Chen","orcid":"https://orcid.org/0000-0003-0341-3428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Chen","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033886915","display_name":"Yi Kang","orcid":"https://orcid.org/0009-0004-3092-5626"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Kang","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100669438"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.86,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86049661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"43","issue":"5","first_page":"1456","last_page":"1469"},"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":0.9998000264167786,"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":0.9995999932289124,"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":0.7661323547363281},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.752173662185669},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5507447123527527},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.49895405769348145},{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.4487874507904053},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.44324079155921936},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4382028579711914},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.41434818506240845},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3996198773384094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3637848496437073},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3258747458457947},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1154966950416565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661323547363281},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.752173662185669},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5507447123527527},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.49895405769348145},{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.4487874507904053},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.44324079155921936},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4382028579711914},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.41434818506240845},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3996198773384094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3637848496437073},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3258747458457947},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1154966950416565},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.0},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2023.3342605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3342605","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G1411627799","display_name":null,"funder_award_id":"XDB44000000","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G2970710660","display_name":null,"funder_award_id":"U19A2074","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4700993392","display_name":null,"funder_award_id":"61874102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7801426869","display_name":null,"funder_award_id":"61931008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8360183649","display_name":null,"funder_award_id":"62141415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W162895179","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1999085092","https://openalex.org/W2011039300","https://openalex.org/W2049287714","https://openalex.org/W2097117768","https://openalex.org/W2118231264","https://openalex.org/W2129960401","https://openalex.org/W2193198328","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2884687835","https://openalex.org/W2896457183","https://openalex.org/W2897083155","https://openalex.org/W2906043559","https://openalex.org/W2912759934","https://openalex.org/W2914250845","https://openalex.org/W2935331687","https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W2997929983","https://openalex.org/W2998732502","https://openalex.org/W3006586535","https://openalex.org/W3015980402","https://openalex.org/W3017521908","https://openalex.org/W3018757597","https://openalex.org/W3111721177","https://openalex.org/W3113331478","https://openalex.org/W3135765046","https://openalex.org/W3136346557","https://openalex.org/W3148444620","https://openalex.org/W4200550987","https://openalex.org/W4213249026","https://openalex.org/W4220702691","https://openalex.org/W4220972538","https://openalex.org/W4235405202","https://openalex.org/W4239722617","https://openalex.org/W4293584584","https://openalex.org/W4295312788","https://openalex.org/W4311609527","https://openalex.org/W4379116009","https://openalex.org/W4380874786","https://openalex.org/W4380881074","https://openalex.org/W4385192563","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6678645334","https://openalex.org/W6684770997","https://openalex.org/W6750227808","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6783602645","https://openalex.org/W6786190416","https://openalex.org/W7002360509"],"related_works":["https://openalex.org/W4293430534","https://openalex.org/W2342813629","https://openalex.org/W3150934690","https://openalex.org/W4297812927","https://openalex.org/W2335743642","https://openalex.org/W2800412005","https://openalex.org/W1976244802","https://openalex.org/W4386903460","https://openalex.org/W1992487929","https://openalex.org/W2083934844"],"abstract_inverted_index":{"With":[0],"the":[1,26,57,64,77,92,118,187,233],"widespread":[2],"use":[3],"of":[4,25,60,67,95,101,108,145,153,191],"deep":[5,132],"neural":[6],"networks":[7],"(DNNs)":[8],"in":[9,165],"intelligent":[10],"systems,":[11],"DNN":[12,48,81,99,103,123,146,155,170,195,215],"accelerators":[13,49],"with":[14,50,218],"high":[15],"performance":[16,52],"and":[17,38,53,63,70,80,98,114,130,161,211,220,226],"energy":[18,54,221],"efficiency":[19],"are":[20],"greatly":[21],"demanded.":[22],"As":[23],"one":[24],"feasible":[27],"processing-in-memory":[28],"(PIM)":[29],"architectures,":[30],"3D-stacked-DRAM-based":[31],"PIM":[32],"(DRAM-PIM)":[33],"architecture":[34,97],"enables":[35],"large-capacity":[36],"memory":[37,40,68],"low-cost":[39],"access,":[41],"which":[42,106],"is":[43],"a":[44,122,131,143],"promising":[45],"solution":[46],"for":[47,125,136,173,207],"better":[51,138],"efficiency.":[55],"However,":[56],"low-access-cost":[58],"characteristics":[59],"stacked":[61],"DRAM":[62,158,166],"distributed":[65],"manner":[66],"access":[69],"data":[71,162,182],"storing":[72],"require":[73],"us":[74],"to":[75,89,167,185,232],"rebalance":[76],"hardware":[78,96,119,139,175,205],"design":[79,93],"mapping.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"NicePIM":[88,202],"efficiently":[90],"explore":[91],"space":[94],"mapping":[100,147,171,216],"DRAM-PIM-based":[102],"inference":[104],"accelerators,":[105],"consists":[107],"three":[109],"key":[110],"components:":[111],"PIM-Tuner,":[112],"PIM-Mapper":[113,141],"Data-Scheduler.":[115],"PIM-Tuner":[116],"optimizes":[117],"configurations":[120,206],"leveraging":[121],"model":[124,135],"classifying":[126],"area-compliant":[127],"PIM-node":[128],"designs":[129],"kernel":[133],"learning":[134],"identifying":[137],"parameters.":[140],"explores":[142],"variety":[144],"configurations,":[148],"including":[149],"parallelism":[150],"between":[151],"branches":[152],"DNN,":[154],"layer":[156,196],"partitioning,":[157],"capacity":[159],"allocation":[160],"layout":[163],"pattern":[164],"generate":[168,213],"high-hardware-utilization":[169],"schemes":[172,217],"various":[174],"configurations.":[176],"The":[177],"Data-Scheduler":[178],"employs":[179],"an":[180],"integer-linear-programming-based":[181],"scheduling":[183],"algorithm":[184],"alleviate":[186],"inter-PIM-node":[188],"communication":[189],"overhead":[190],"data-sharing":[192],"brought":[193],"by":[194,224],"partitioning.":[197],"Experimental":[198],"results":[199],"demonstrate":[200],"that":[201],"can":[203,212],"optimize":[204],"DRAM-PIM":[208],"systems":[209],"effectively":[210],"high-quality":[214],"latency":[219],"cost":[222],"reduced":[223],"37%":[225],"28%":[227],"on":[228],"average":[229],"respectively":[230],"compared":[231],"baseline":[234],"method.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
