{"id":"https://openalex.org/W4410770865","doi":"https://doi.org/10.1109/tcad.2025.3574235","title":"Throughput Maximization for Transformer Inference on Processing Near-Memory Architectures","display_name":"Throughput Maximization for Transformer Inference on Processing Near-Memory Architectures","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410770865","doi":"https://doi.org/10.1109/tcad.2025.3574235"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2025.3574235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3574235","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/A5032602090","display_name":"Mengke Ge","orcid":"https://orcid.org/0000-0001-7888-9370"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mengke Ge","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113152317","display_name":"Yingjian Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjian Zhong","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423614","display_name":"Song Chen","orcid":"https://orcid.org/0000-0003-0341-3428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Chen","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103907350","display_name":"Yi Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Kang","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032602090"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9547633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"45","issue":"1","first_page":"120","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.887499988079071,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10320","display_name":"Neural Networks and Applications","score":0.887499988079071,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.8614000082015991,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.8586000204086304,"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/inference","display_name":"Inference","score":0.6569138765335083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6138547658920288},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.529914140701294},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5227805972099304},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5031868815422058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27927476167678833},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11262741684913635},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10783833265304565},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10153493285179138}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6569138765335083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6138547658920288},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.529914140701294},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5227805972099304},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5031868815422058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27927476167678833},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11262741684913635},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10783833265304565},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10153493285179138},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3574235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3574235","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","score":0.5299999713897705,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1085865041","display_name":null,"funder_award_id":"92473114","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2118231264","https://openalex.org/W2606722458","https://openalex.org/W2626991402","https://openalex.org/W2896457183","https://openalex.org/W2935331687","https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W2980200167","https://openalex.org/W3085277063","https://openalex.org/W3100710793","https://openalex.org/W3102790199","https://openalex.org/W3131500599","https://openalex.org/W3135352626","https://openalex.org/W3136346557","https://openalex.org/W3138516171","https://openalex.org/W3159727696","https://openalex.org/W3167366661","https://openalex.org/W3185889905","https://openalex.org/W3192336523","https://openalex.org/W3197778677","https://openalex.org/W3211180228","https://openalex.org/W3213412675","https://openalex.org/W3214374352","https://openalex.org/W4213019189","https://openalex.org/W4214686755","https://openalex.org/W4220865834","https://openalex.org/W4220972538","https://openalex.org/W4221001402","https://openalex.org/W4239722617","https://openalex.org/W4246587277","https://openalex.org/W4280489237","https://openalex.org/W4280496502","https://openalex.org/W4280562683","https://openalex.org/W4285601701","https://openalex.org/W4297097345","https://openalex.org/W4297097426","https://openalex.org/W4311609527","https://openalex.org/W4318541578","https://openalex.org/W4321636575","https://openalex.org/W4323519269","https://openalex.org/W4327930465","https://openalex.org/W4360831795","https://openalex.org/W4380881063","https://openalex.org/W4380881077","https://openalex.org/W4385192563","https://openalex.org/W4385245566","https://openalex.org/W4389491911","https://openalex.org/W4389692499","https://openalex.org/W4394931151","https://openalex.org/W4403636247","https://openalex.org/W4404101614","https://openalex.org/W4404483424","https://openalex.org/W4406172504"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,64,83,181,207],"Transformers":[3,85,135,183],"has":[4,35],"revolutionized":[5],"fields":[6],"such":[7,26],"as":[8,27,37],"computer":[9],"vision":[10],"and":[11,29,66,96,151,161,209],"natural":[12],"language":[13],"processing.":[14],"However,":[15,47],"their":[16],"memory-intensive":[17],"nature":[18],"creates":[19],"significant":[20],"hurdles":[21],"for":[22,134,165],"conventional":[23],"computing":[24],"platforms":[25],"CPUs":[28],"GPUs.":[30],"Processing":[31],"near-memory":[32],"(PNM)":[33],"architecture":[34,54],"arisen":[36],"a":[38,56,71,102,166],"promising":[39],"solution":[40],"to":[41,79,93,121,128,136,156,193,211],"mitigate":[42],"the":[43,61,129,144,178,201],"memory":[44],"wall":[45],"problem.":[46],"efficiently":[48],"deploying":[49],"Transformer":[50],"models":[51],"on":[52,86,108,184],"PNM":[53,185],"remains":[55],"cutting-edge":[57],"challenge.":[58],"To":[59],"address":[60],"practical":[62],"demands":[63],"cloud":[65],"edge":[67],"computing,":[68],"we":[69],"propose":[70],"novel":[72,103],"mapping":[73,145,169,189],"framework":[74],"called":[75],"Energon,":[76],"which":[77,112],"aims":[78],"facilitate":[80],"high-throughput":[81],"inference":[82,179,202],"encoderbased":[84],"PNM-based":[87],"neural":[88],"network":[89,159],"(NN)":[90],"accelerators,":[91,186],"catering":[92],"both":[94],"non-latency-sensitive":[95],"latencybounded":[97],"scenarios.":[98],"Firstly,":[99],"Energon":[100,142,175],"introduces":[101],"pipeline":[104,118,123,162],"parallelism":[105,124],"strategy":[106],"based":[107],"an":[109,114,205],"XY-aligned":[110],"layout,":[111],"offers":[113],"enhanced":[115],"flexibility":[116],"in":[117],"layout":[119,163],"compared":[120],"existing":[122],"approaches,":[125],"while":[126],"adapting":[127],"finegrained":[130],"partitioning":[131,160],"scheme":[132],"tailored":[133],"achieve":[137],"efficient":[138],"mass":[139],"parallelism.":[140],"Secondly,":[141],"formulates":[143],"optimization":[146],"problems":[147],"using":[148],"dynamic":[149],"programming":[150],"integer":[152],"linear":[153],"programming,":[154],"respectively,":[155],"jointly":[157],"optimize":[158],"construction":[164],"globally":[167],"optimal":[168],"solution.":[170],"Experimental":[171],"results":[172],"demonstrate":[173],"that":[174],"significantly":[176],"improves":[177],"throughput":[180,203],"encoder-based":[182],"outperforming":[187],"state-of-the-art":[188],"frameworks":[190],"by":[191,204],"1.1\u00d7":[192],"2.3\u00d7.":[194],"Under":[195],"user-defined":[196],"latency":[197],"bounds,":[198],"it":[199],"enhances":[200],"average":[206],"43%":[208],"up":[210],"123%.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}