Parmar, VivekVivekParmarMüller, FranzFranzMüllerHsuen, Jing-HuaJing-HuaHsuenKingra, Sandeep KaurSandeep KaurKingraLaleni, NelliNelliLaleniRaffel, YannickYannickRaffelLederer, MaximilianMaximilianLedererVardar, AlptekinAlptekinVardarSeidel, KonradKonradSeidelSoliman, TahaTahaSolimanKirchner, TobiasTobiasKirchnerAli, TarekTarekAliDünkel, StefanStefanDünkelBeyer, SvenSvenBeyerWu, Tian-LiTian-LiWuDe, SouravSouravDeSuri, MananMananSuriKämpfe, ThomasThomasKämpfe2024-03-062024-03-062023https://publica.fraunhofer.de/handle/publica/46293010.1002/aisy.2022003892-s2.0-85165801319Harnessing multibit precision in nonvolatile memory (NVM)-based synaptic core can accelerate multiply and accumulate (MAC) operation of deep neural network (DNN). However, NVM-based synaptic cores suffer from the trade-off between bit density and performance. The undesired performance degradation with scaling, limited bit precision, and asymmetry associated with weight update poses a severe bottleneck in realizing a high-density synaptic core. Herein, 1) evaluation of novel differential mode ferroelectric field-effect transistor (DM-FeFET) bitcell on a crossbar array of 4 K devices; 2) validation of weighted sum operation on 28 nm DM-FeFET crossbar array; 3) bit density of 223Mb mm-2, which is ≈2× improvement compared to conventional FeFET array; 4) 196 TOPS/W energy efficiency for VGG-8 network; and 5) superior bit error rate (BER) resilience showing ≈94% training and 88% inference accuracy with 1% BER are demonstrated.enconvolutional neural network (CNN)ferroelectric field-effect transistor (FeFET)in-memory computing (IMC)nonvolatile memory (NVM)journal article