Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312746619> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4312746619 abstract "We propose a novel Reinforcement Learning (RL) and Simulated Annealing (SA)-based placement algorithm (RS3DPlace), which, to the best of our knowledge, is the first machine learning approach for Monolithic 3D ICs (M3D). Application of Machine Learning to physical design of 2D and 3D VLSI ICs is an emerging area. Recently proposed learning algorithms for the placement problem consider only 2D ICs and still exhibit memory issues and learning problems in large search spaces. RS3DPlace uses the learning ability of RL to quickly estimate a preliminary solution, which SA later uses to generate an improved final solution. To address memory issues, RS3DPlace uses the approximate method for state representation which reduces the memory complexity and allows more than one kind of perturbation to improve learning efficiency in large search spaces. The current implementation is for the gate-level M3D design style, but it can be extended to other M3D design styles and other 2D and 3D physical design optimization problems. To illustrate the effectiveness of RS3DPlace, we tested it for 8-128-bit MUX-based right arithmetic shifter circuits and a circuit with non-regular connections compared to Mux-based shifters, which are optimized in 2-layered M3D technology. The experimental results show that RS3DPlace solves the M3D placement of 896 variables. Experimental results also show on average 16% improvement in overall cost function in comparison to Random Initialized SA (RandSA)." @default.
- W4312746619 created "2023-01-05" @default.
- W4312746619 creator A5040622659 @default.
- W4312746619 creator A5046901640 @default.
- W4312746619 date "2022-05-28" @default.
- W4312746619 modified "2023-10-16" @default.
- W4312746619 title "RS3DPlace: Monolithic 3D IC placement using Reinforcement Learning and Simulated Annealing" @default.
- W4312746619 cites W2002806561 @default.
- W4312746619 cites W2063821970 @default.
- W4312746619 cites W2085968419 @default.
- W4312746619 cites W2089979174 @default.
- W4312746619 cites W2127725283 @default.
- W4312746619 cites W2538167498 @default.
- W4312746619 cites W2614764752 @default.
- W4312746619 cites W2745285691 @default.
- W4312746619 cites W2768265037 @default.
- W4312746619 cites W2775005974 @default.
- W4312746619 cites W2787438330 @default.
- W4312746619 cites W2790792381 @default.
- W4312746619 cites W3110928049 @default.
- W4312746619 cites W3161923038 @default.
- W4312746619 cites W4246766117 @default.
- W4312746619 doi "https://doi.org/10.1109/iscas48785.2022.9937281" @default.
- W4312746619 hasPublicationYear "2022" @default.
- W4312746619 type Work @default.
- W4312746619 citedByCount "0" @default.
- W4312746619 crossrefType "proceedings-article" @default.
- W4312746619 hasAuthorship W4312746619A5040622659 @default.
- W4312746619 hasAuthorship W4312746619A5046901640 @default.
- W4312746619 hasConcept C111919701 @default.
- W4312746619 hasConcept C113775141 @default.
- W4312746619 hasConcept C11413529 @default.
- W4312746619 hasConcept C124584101 @default.
- W4312746619 hasConcept C126980161 @default.
- W4312746619 hasConcept C139719470 @default.
- W4312746619 hasConcept C14580979 @default.
- W4312746619 hasConcept C149635348 @default.
- W4312746619 hasConcept C154945302 @default.
- W4312746619 hasConcept C162324750 @default.
- W4312746619 hasConcept C19275194 @default.
- W4312746619 hasConcept C41008148 @default.
- W4312746619 hasConcept C530198007 @default.
- W4312746619 hasConcept C70970002 @default.
- W4312746619 hasConcept C76155785 @default.
- W4312746619 hasConcept C97541855 @default.
- W4312746619 hasConceptScore W4312746619C111919701 @default.
- W4312746619 hasConceptScore W4312746619C113775141 @default.
- W4312746619 hasConceptScore W4312746619C11413529 @default.
- W4312746619 hasConceptScore W4312746619C124584101 @default.
- W4312746619 hasConceptScore W4312746619C126980161 @default.
- W4312746619 hasConceptScore W4312746619C139719470 @default.
- W4312746619 hasConceptScore W4312746619C14580979 @default.
- W4312746619 hasConceptScore W4312746619C149635348 @default.
- W4312746619 hasConceptScore W4312746619C154945302 @default.
- W4312746619 hasConceptScore W4312746619C162324750 @default.
- W4312746619 hasConceptScore W4312746619C19275194 @default.
- W4312746619 hasConceptScore W4312746619C41008148 @default.
- W4312746619 hasConceptScore W4312746619C530198007 @default.
- W4312746619 hasConceptScore W4312746619C70970002 @default.
- W4312746619 hasConceptScore W4312746619C76155785 @default.
- W4312746619 hasConceptScore W4312746619C97541855 @default.
- W4312746619 hasLocation W43127466191 @default.
- W4312746619 hasOpenAccess W4312746619 @default.
- W4312746619 hasPrimaryLocation W43127466191 @default.
- W4312746619 hasRelatedWork W1520485098 @default.
- W4312746619 hasRelatedWork W1623109264 @default.
- W4312746619 hasRelatedWork W2006252341 @default.
- W4312746619 hasRelatedWork W2036873162 @default.
- W4312746619 hasRelatedWork W2040050847 @default.
- W4312746619 hasRelatedWork W2081276259 @default.
- W4312746619 hasRelatedWork W2114478082 @default.
- W4312746619 hasRelatedWork W2151912830 @default.
- W4312746619 hasRelatedWork W3027537505 @default.
- W4312746619 hasRelatedWork W4236150881 @default.
- W4312746619 isParatext "false" @default.
- W4312746619 isRetracted "false" @default.
- W4312746619 workType "article" @default.