{"id":"https://openalex.org/W7134934393","doi":"https://doi.org/10.1109/asp-dac66049.2026.11420699","title":"Boosting Scalability and Performance: Macro Placement for Flexible 3D-Stacked ML Accelerators","display_name":"Boosting Scalability and Performance: Macro Placement for Flexible 3D-Stacked ML Accelerators","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7134934393","doi":"https://doi.org/10.1109/asp-dac66049.2026.11420699"},"language":null,"primary_location":{"id":"doi:10.1109/asp-dac66049.2026.11420699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asp-dac66049.2026.11420699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022607314","display_name":"Jiawei Hu","orcid":"https://orcid.org/0000-0002-5584-2462"},"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":"Jiawei Hu","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439626","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0002-2972-7639"},"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":"Canlin Zhang","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073660004","display_name":"Pruek Vanna-Iampikul","orcid":"https://orcid.org/0000-0002-2897-7142"},"institutions":[{"id":"https://openalex.org/I129488602","display_name":"Burapha University","ror":"https://ror.org/01ff74m36","country_code":"TH","type":"education","lineage":["https://openalex.org/I129488602"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pruek Vanna-Iampikul","raw_affiliation_strings":["Burapha University,Department of Electrical Engineering,Chonburi,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Burapha University,Department of Electrical Engineering,Chonburi,Thailand","institution_ids":["https://openalex.org/I129488602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124285599","display_name":"Tushar Krishna","orcid":null},"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":"Tushar Krishna","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052950521","display_name":"Sung Kyu Lim","orcid":"https://orcid.org/0000-0002-2267-5282"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sung Kyu Lim","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"979","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8583999872207642,"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":0.8583999872207642,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.01940000057220459,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.007899999618530273,"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/boosting","display_name":"Boosting (machine learning)","score":0.746999979019165},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.529699981212616},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.46230000257492065},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.24459999799728394}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633999943733215},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.24459999799728394},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2401999980211258},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.23970000445842743},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.22789999842643738}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asp-dac66049.2026.11420699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asp-dac66049.2026.11420699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2906043559","https://openalex.org/W2953212265","https://openalex.org/W3016542674","https://openalex.org/W3097528158","https://openalex.org/W4244024631","https://openalex.org/W4249932213","https://openalex.org/W4293024984","https://openalex.org/W4362653371","https://openalex.org/W4385859348","https://openalex.org/W4389383710","https://openalex.org/W4401212157"],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"accelerators":[3],"increasingly":[4],"demand":[5],"architectural":[6,68],"flexibility":[7],"to":[8,106,124],"support":[9],"diverse":[10],"workloads.":[11],"While":[12],"reconfigurable":[13],"designs":[14],"like":[15],"Self-Adaptive":[16],"Reconfigurable":[17],"Arrays":[18],"(SARA)":[19],"improve":[20],"adaptability,":[21],"they":[22],"suffer":[23],"from":[24],"physical":[25],"design":[26],"bottlenecks-particularly":[27],"in":[28],"memory-intensive":[29],"settings":[30],"where":[31],"dense":[32],"memory":[33],"integration":[34,52],"inflates":[35],"area,":[36],"wirelength,":[37],"and":[38,58,84,96,117],"energy":[39],"consumption.":[40],"To":[41],"address":[42],"these":[43],"challenges,":[44],"we":[45],"propose":[46],"a":[47],"scalable":[48],"multi-tier":[49,85],"memory-on-logic":[50],"(MoL)":[51],"framework":[53],"that":[54],"co-optimizes":[55],"macro":[56],"placement":[57],"standard-cell":[59],"layout":[60],"for":[61,74,81],"flexible":[62],"ML":[63,102,136],"accelerators.":[64,137],"Our":[65],"methodology":[66],"combines":[67],"insights":[69],"with":[70],"subgradient-based":[71],"convex":[72],"optimization":[73],"global":[75],"placement,":[76],"followed":[77],"by":[78],"simulated":[79],"annealing":[80],"overlap":[82],"resolution":[83],"partitioning.":[86],"The":[87],"proposed":[88],"flow":[89],"significantly":[90],"improves":[91],"area":[92,121],"efficiency,":[93],"routing":[94],"congestion,":[95],"timing":[97],"closure.":[98],"Experimental":[99],"results":[100],"on":[101],"workloads":[103],"demonstrate":[104],"up":[105],"3.4":[107],"\u00d7":[108,112],"runtime":[109],"speedup,":[110],"4.4":[111],"energy-delay":[113],"product":[114],"(EDP)":[115],"improvement,":[116],"$2.3":[118],"\\times$":[119],"chip":[120],"reduction":[122],"compared":[123],"conventional":[125],"two-tier":[126],"MoL":[127],"baselines,":[128],"enabling":[129],"practical":[130],"deployment":[131],"of":[132],"high-performance,":[133],"adaptive":[134],"3D":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-12T00:00:00"}