{"id":"https://openalex.org/W4416429527","doi":"https://doi.org/10.1109/iccad66269.2025.11240989","title":"CIMWise: An IREE-based End-To-End AI Compiler with Auto-Tuning for CIM Processors","display_name":"CIMWise: An IREE-based End-To-End AI Compiler with Auto-Tuning for CIM Processors","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429527","doi":"https://doi.org/10.1109/iccad66269.2025.11240989"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5120557589","display_name":"Bo Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Mai","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113414416","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0002-8298-4378"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120658444","display_name":"Zhen Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhai","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425268","display_name":"Liang Zhang","orcid":"https://orcid.org/0000-0003-1566-4902"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084697396","display_name":"Yufu Zhang","orcid":"https://orcid.org/0000-0003-0648-2058"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufu Zhang","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021091015","display_name":"Longyang Lin","orcid":"https://orcid.org/0000-0002-4702-737X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Lin","raw_affiliation_strings":["Southern University of Science and Technology,School of Microelectronics,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Microelectronics,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120557589"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38096714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.23469999432563782,"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":0.23469999432563782,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.16200000047683716,"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/T14347","display_name":"Big Data and Digital Economy","score":0.155799999833107,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/dataflow","display_name":"Dataflow","score":0.8906999826431274},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7279000282287598},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5942999720573425},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5422999858856201},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5375000238418579},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.5309000015258789},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4018999934196472}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8906999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137000203132629},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7279000282287598},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.5309000015258789},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48019999265670776},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.45649999380111694},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2913104037","https://openalex.org/W3031771821","https://openalex.org/W3204737618","https://openalex.org/W3212662098","https://openalex.org/W4205230840","https://openalex.org/W4243519499","https://openalex.org/W4292169167","https://openalex.org/W4385896568","https://openalex.org/W4394998365","https://openalex.org/W4409328995","https://openalex.org/W4410492686"],"related_works":[],"abstract_inverted_index":{"Computing-In-memory":[0],"(CIM)":[1],"processors":[2,41],"have":[3],"emerged":[4],"as":[5],"a":[6,28,89,108,130,158,197,204],"promising":[7],"approach":[8],"for":[9,95,141,153],"accelerating":[10],"deep":[11],"neural":[12,175],"networks":[13,176],"(DNNs).":[14],"To":[15],"unleash":[16],"the":[17,36,75,142,166],"potential":[18],"of":[19,34,39,47,77,174],"diverse":[20],"CIM":[21,40,43,48,58,66,96,146,178,212],"architectures,":[22],"it":[23],"is":[24,32,183],"essential":[25],"to":[26,136,161,196,210],"develop":[27],"tailored":[29],"compiler":[30,94],"that":[31,192],"aware":[33],"both":[35,113],"architectural":[37],"parameters":[38,115],"(e.g.,":[42,57],"array":[44],"size,":[45],"number":[46],"units,":[49],"on-chip":[50,126],"buffer":[51,62],"capacity)":[52],"and":[53,116,129,156,203],"their":[54],"dataflow":[55,60,78,117],"characteristics":[56],"parallelism,":[59],"scheduling,":[61],"allocation).":[63],"However,":[64],"existing":[65],"compilers":[67],"primarily":[68],"focus":[69],"on":[70,145,177],"hardware":[71,114,187],"parameters,":[72],"while":[73],"neglecting":[74],"diversity":[76],"patterns":[79],"across":[80],"different":[81],"architectures.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"CIMWise,":[88],"general,":[90],"IREE-based,":[91],"end-to-end":[92,172],"AI":[93],"processors.":[97,147,179],"At":[98],"its":[99],"core,":[100],"an":[101,119,124],"auto-tuning":[102,168],"framework":[103],"has":[104],"been":[105],"developed,":[106],"comprising":[107],"comprehensive":[109],"search":[110,134],"space":[111],"(including":[112],"characteristics),":[118],"analytical":[120],"cost":[121],"model":[122],"(integrating":[123],"adaptable":[125],"memory":[127],"model),":[128],"two-stage":[131],"simulated":[132],"annealing":[133],"algorithm,":[135],"explore":[137],"optimal":[138],"scheduling":[139],"strategies":[140],"target":[143],"workload":[144],"Additionally,":[148],"CIMWise":[149,182,193],"leverages":[150],"IREE\u2019s":[151],"frontend":[152],"graph-level":[154],"optimization":[155,164],"implements":[157],"customized":[159],"backend":[160],"perform":[162],"operator-level":[163],"using":[165],"proposed":[167,181],"framework,":[169],"enabling":[170],"seamless":[171],"deployment":[173],"The":[180],"validated":[184],"through":[185],"actual":[186],"measurements.":[188],"Experimental":[189],"results":[190],"show":[191],"achieves":[194],"up":[195],"58%":[198],"reduction":[199],"in":[200,207],"energy":[201],"consumption":[202],"19%":[205],"decrease":[206],"latency":[208],"compared":[209],"prior":[211],"compilers.":[213]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-20T00:00:00"}