{"id":"https://openalex.org/W7164131799","doi":"https://doi.org/10.1109/fccm68464.2026.00015","title":"The Optimal, The Fast, and The Hybrid: Automatic Placement and Routing for AIE Arrays","display_name":"The Optimal, The Fast, and The Hybrid: Automatic Placement and Routing for AIE Arrays","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7164131799","doi":"https://doi.org/10.1109/fccm68464.2026.00015"},"language":null,"primary_location":{"id":"doi:10.1109/fccm68464.2026.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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/A5068360756","display_name":"Hang Yan","orcid":"https://orcid.org/0000-0002-3386-8784"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hang Yan","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127706826","display_name":"James Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Yen","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138299593","display_name":"Rongbo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rongbo Zhang","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090801235","display_name":"Andrew Boutros","orcid":"https://orcid.org/0000-0002-8044-1644"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew Boutros","raw_affiliation_strings":["University of Waterloo,Department of Electrical and Computer Engineering,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Electrical and Computer Engineering,Toronto,Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138373520","display_name":"Vaughn Betz","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vaughn Betz","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.6575,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99031608,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.2159000039100647,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.2159000039100647,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.08150000125169754,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.061900001019239426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5011000037193298},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2791000008583069},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.24789999425411224},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.24160000681877136},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2410999983549118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319000124931335},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.24789999425411224},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24160000681877136},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2410999983549118},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22840000689029694},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2222999930381775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm68464.2026.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2024060531","https://openalex.org/W2139637699","https://openalex.org/W2150807309","https://openalex.org/W2915644294","https://openalex.org/W2918037051","https://openalex.org/W2981712449","https://openalex.org/W3138319291","https://openalex.org/W4318719410","https://openalex.org/W4319870545","https://openalex.org/W4321637087","https://openalex.org/W4321637250","https://openalex.org/W4321637356","https://openalex.org/W4376130831","https://openalex.org/W4381328365","https://openalex.org/W4383749471","https://openalex.org/W4388214721","https://openalex.org/W4391455288","https://openalex.org/W4391988115","https://openalex.org/W4400489024","https://openalex.org/W4401331008","https://openalex.org/W4402475817","https://openalex.org/W4403279027","https://openalex.org/W4407953492","https://openalex.org/W4410344137","https://openalex.org/W4410810249","https://openalex.org/W4412203320","https://openalex.org/W4414348392","https://openalex.org/W4417260734"],"related_works":[],"abstract_inverted_index":{"Most":[0],"of":[1,28,48,60,90,135,149,232,303,316],"the":[2,81,132,159,312,322],"widely":[3],"deployed":[4],"deep":[5],"learning":[6],"(DL)":[7],"workloads,":[8],"such":[9,65,91],"as":[10,66,247],"large":[11],"language":[12],"models":[13],"and":[14,84,166,221,273,290,359],"convolutional":[15],"neural":[16],"networks,":[17],"are":[18,33,88,116,123,139,360],"relatively":[19],"regular":[20,199],"compute":[21,29,50,106,114],"graphs":[22],"that":[23,42,122,157,235,253,346,351],"exhibit":[24],"a":[25,34,109,153,163,217,230,248,297,353],"high":[26,95],"degree":[27],"parallelism.":[30],"Therefore,":[31],"they":[32],"natural":[35],"fit":[36],"for":[37,175,198,208,225,241,283,300],"spatial":[38],"dataflow":[39],"accelerator":[40],"architectures":[41,103],"map":[43],"computations":[44],"to":[45,101,104,141,161,311,334],"an":[46,275],"array":[47],"many":[49],"cores":[51,121],"communicating":[52],"via":[53],"shared":[54],"memory":[55],"buffers":[56],"and/or":[57],"some":[58],"form":[59],"flexible":[61],"interconnect":[62],"between":[63,146],"them,":[64],"circuit":[67],"or":[68,182,195,205,238],"packet":[69],"switched":[70],"networks-on-chip":[71],"(NoCs).":[72],"AMD\u2019s":[73,269,317,339,357],"adaptive":[74],"intelligent":[75],"engine":[76],"(AIE)":[77],"arrays":[78,177],"in":[79,321],"both":[80],"Versal":[82],"FPGAs":[83],"Ryzen":[85],"NPU":[86],"devices":[87],"exemplars":[89],"architectures.":[92],"Despite":[93],"their":[94,280],"peak":[96],"performance,":[97],"efficiently":[98],"mapping":[99,165,299],"workloads":[100],"these":[102,150],"maximize":[105],"utilization":[107],"is":[108,152,254],"challenging":[110],"task.":[111],"The":[112,171],"application\u2019s":[113],"kernels":[115],"first":[117],"partitioned":[118],"into":[119,268],"logical":[120],"then":[124],"placed":[125],"at":[126],"specific":[127],"physical":[128],"core":[129],"locations.":[130],"Finally,":[131],"different":[133],"types":[134],"inter-core":[136],"communication":[137],"resources":[138],"configured":[140],"realize":[142],"efficient":[143],"data":[144],"movement":[145],"cores.":[147],"Each":[148],"steps":[151],"complex":[154],"optimization":[155],"problem":[156,252],"determines":[158],"ability":[160],"find":[162],"feasible":[164],"directly":[167],"impacts":[168],"performance":[169,285],"results.":[170],"current":[172],"programming":[173,281],"model":[174],"AIE":[176,226],"relies":[178],"on":[179],"manual":[180,335,366],"placement":[181,220,233,336],"uses":[183],"greedy":[184,318],"2D":[185],"tiling":[186],"algorithms.":[187],"These":[188],"approaches":[189],"either":[190],"require":[191],"significant":[192],"designer":[193],"effort":[194],"work":[196,215],"only":[197,361],"2D-structured":[200],"computations,":[201],"but":[202],"produce":[203],"poor-quality":[204],"unroutable":[206],"solutions":[207,350],"other":[209],"cases.":[210],"To":[211,260],"this":[212,214],"end,":[213],"presents":[216],"versatile":[218],"automatic":[219],"routing":[222,246,328],"(PnR)":[223],"framework":[224,295],"arrays.":[227],"We":[228,243],"evaluate":[229],"variety":[231],"algorithms":[234],"guarantee":[236],"optimality":[237,240],"trade":[239],"scalability.":[242],"also":[244,326],"formulate":[245],"modified":[249],"multi-commodity":[250],"flow":[251],"solved":[255],"using":[256,279],"mixed-integer":[257],"linear":[258],"programming.":[259],"demonstrate":[261],"our":[262,293,347],"PnR":[263,294,348],"framework,":[264],"we":[265],"integrate":[266],"it":[267],"open-source":[270],"MLIR-AIE":[271,323],"toolchain":[272],"develop":[274],"entire":[276],"benchmark":[277],"suite":[278],"API":[282],"end-to-end":[284,342],"evaluation.":[286],"Across":[287],"202":[288,304],"synthetic":[289],"real-world":[291],"benchmarks,":[292],"finds":[296],"legal":[298],"200":[301],"out":[302],"benchmarks":[305],"(a":[306],"99%":[307],"success":[308,314],"rate)":[309],"compared":[310,333],"62%":[313],"rate":[315],"sequential":[319],"placer":[320,358],"toolchain.":[324],"It":[325],"reduces":[327],"resource":[329],"usage":[330],"by":[331,338],"15%":[332],"followed":[337],"router.":[340],"On-device":[341],"runtime":[343],"measurements":[344],"show":[345],"produces":[349],"have":[352],"30%":[354],"speedup":[355],"over":[356],"7%":[362],"slower":[363],"than":[364],"expert":[365],"placement.":[367]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2026-06-11T00:00:00"}