DC25_SLIDES_Track14_DeepReinforcementLearningBasedDesign_Ryu 2025-01-21 16.32.01.pdf

1、Information Classification:GeneralWelcome to ConferenceJanuary 2830,2025Santa Clara Convention Center1ExpoJanuary 2930,2025Information Classification:GeneralDeep Reinforcement Learning Based Design Optimization of Power/Ground Ball Map in BGA Package in 3D-ICs Considering Multiple Power Domain Envir

2、onmentsSpeaker:Seunghun Ryu,(KAIST)Dongryul Park(KAIST),Seonghi Lee(KAIST),Hyunwoong Kim(Samsung Electronics)Sanguk Lee(KAIST),Hyunwoo Kim(KAIST),Seongho Woo(KAIST),Changmin Lee(KAIST),Jaewon Rhee(KAIST),Seokbeom Yong(Samsung Electronics),Sangsub Song(Samsung Electronics),Jiseong Kim(KAIST),Seungyou

3、ng Ahn(KAIST)2Information Classification:GeneralSPEAKERSSeunghun RyuPh.D Student,Korea Advanced Institute of Science and Technology(KAIST)ysh0067kaist.ac.krSeunghun Ryu received the M.S.degree from The Cho Chun Shik Graduate School of Mobility,Korea Advanced Institute of Science and Technology(KAIST

4、),Daejeon,South Korea,in 2022,where he is currently pursuing the Ph.D.degree.In 2022,he was a visiting scholar at Missouri University of Science and Technology,Rolla,MO.Research interest:High-speed interconnection design,machine learning-based power integrity design optimization for 2.5D/3D ICs3Info

5、rmation Classification:GeneralContents4I.IntroductionII.Proposal of a Power/Ground Ball Map Design Optimization MethodA.Markov Decision Process ConfigurationB.Reward Calculation based on the Analytical ModelC.Network Configuration and Training AlgorithmIII.Verification of the Proposed MethodA.Traini

6、ng ConfigurationB.Optimality PerformanceIV.ConclusionInformation Classification:GeneralContents5I.IntroductionII.Proposal of a Power/Ground Ball Map Design Optimization MethodA.Markov Decision Process ConfigurationB.Reward Calculation based on the Analytical ModelC.Network Configuration and Training