{"id":"https://openalex.org/W7106149110","doi":"https://doi.org/10.1109/iccad66269.2025.11240861","title":"(Invited) Generalized GPU-Accelerated Dynamic Programming with Application to Mixed-Cell-Height Detailed Placement","display_name":"(Invited) Generalized GPU-Accelerated Dynamic Programming with Application to Mixed-Cell-Height Detailed Placement","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7106149110","doi":"https://doi.org/10.1109/iccad66269.2025.11240861"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240861","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":"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":null,"display_name":"Da-Wei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Wei Huang","raw_affiliation_strings":["National Taiwan University of Science and Technology,Department of Electrical Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Department of Electrical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shao-Yun Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Yun Fang","raw_affiliation_strings":["National Taiwan University of Science and Technology,Department of Electrical Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Department of Electrical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wen-Hao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wen-Hao Liu","raw_affiliation_strings":["NVIDIA,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.6762999892234802,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.6762999892234802,"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":0.12229999899864197,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.08420000225305557,"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/scalability","display_name":"Scalability","score":0.692799985408783},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5471000075340271},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.460099995136261},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4307999908924103},{"id":"https://openalex.org/keywords/quadratic-programming","display_name":"Quadratic programming","score":0.3756999969482422},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3720000088214874},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.34860000014305115},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3343000113964081},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123000264167786},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.692799985408783},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C188817802","wikidata":"https://www.wikidata.org/wiki/Q13426855","display_name":"Physical design","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240861","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":[{"score":0.4421772360801697,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1990485341","https://openalex.org/W2008232174","https://openalex.org/W2116110120","https://openalex.org/W2123316553","https://openalex.org/W2140411614","https://openalex.org/W2160252016","https://openalex.org/W2172629440","https://openalex.org/W2398997130","https://openalex.org/W2604305190","https://openalex.org/W2901994323","https://openalex.org/W3005126554","https://openalex.org/W3036696276","https://openalex.org/W3107950019","https://openalex.org/W3111098492","https://openalex.org/W3114262462","https://openalex.org/W4200208073","https://openalex.org/W4280571788","https://openalex.org/W4312121154","https://openalex.org/W4389166755","https://openalex.org/W4404133739"],"related_works":[],"abstract_inverted_index":{"Dynamic":[0],"programming":[1],"(DP)":[2],"plays":[3],"a":[4,48,63,68],"crucial":[5],"role":[6],"as":[7],"the":[8,16,84,119],"backbone":[9],"of":[10,87,109,121],"many":[11],"core":[12],"optimization":[13],"algorithms":[14],"across":[15],"physical":[17,138],"design":[18,134,139],"flow,":[19],"including":[20],"placement,":[21],"clock":[22],"tree":[23],"synthesis,":[24],"and":[25,90,111],"routing.":[26],"However,":[27],"DP":[28,51,80],"methods":[29],"with":[30],"quadratic":[31],"or":[32],"higher":[33],"time":[34],"complexities":[35],"often":[36],"face":[37],"scalability":[38],"challenges":[39],"in":[40,136],"large-scale":[41],"designs.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,66],"propose":[47],"novel":[49],"GPU-accelerated":[50,69],"technique":[52],"that":[53],"can":[54],"be":[55],"broadly":[56],"adaptable":[57],"to":[58,126,132],"various":[59],"DP-based":[60],"algorithms.":[61],"As":[62],"case":[64],"study,":[65],"present":[67],"detailed":[70],"placement":[71,101],"framework":[72],"targeting":[73],"mixed-cell-height":[74],"designs,":[75],"built":[76],"upon":[77],"an":[78,105],"optimal":[79,100],"formulation.":[81],"By":[82],"leveraging":[83],"massive":[85],"parallelism":[86],"modern":[88],"GPUs":[89],"incorporating":[91],"advanced":[92,137],"cost":[93],"accumulation":[94],"strategies,":[95],"our":[96],"approach":[97],"consistently":[98],"delivers":[99],"solutions":[102],"while":[103],"achieving":[104],"average":[106],"runtime":[107,128],"reduction":[108],"96.6%":[110],"peak":[112],"speedups":[113],"exceeding":[114],"1600\u00d7.":[115],"This":[116],"work":[117],"demonstrates":[118],"potential":[120],"GPU":[122],"acceleration":[123],"not":[124],"only":[125],"overcome":[127],"bottlenecks":[129],"but":[130],"also":[131],"enhance":[133],"quality":[135],"tasks.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-20T00:00:00"}