Title
Ferroelectrics: From Memory to Computing
Abstract
Research discovery of ferroelectricity in doped hafnium dioxide thin films has ignited tremendous activity in exploration of ferroelectric FETs for a range of applications from low-power logic to embedded non-volatile memory to in-memory compute kernels. In this paper, key milestones in the evolution of Ferroelectric Field Effect Transistors (FeFETs) and the emergence of a versatile ferroelectronic platform are presented. FeFET exhibits superior energy efficiency and high performance as embedded nonvolatile memory. When embedded into logic, such as SRAM or D-flip-flop, nonvolatile processor can be designed, which is critical for intermittent computing with unreliable power. The partial polarization switching in multi-domain ferroelectric can be harnessed to develop analog synaptic weight cell for deep learning accelerators. To further improve the energy-efficiency of computation, ferroelectric in-memory computing hardware primitive is designed, with one prominent example of ferroelectric TCAM. Utilizing the ferroelectric switching dynamics, ferroelectric neuron with intrinsic homeostasis can be realized to enable a unified ferroelectric platform for spiking neural network. From all these developments, ferroelectric emerges as a highly promising platform for various exciting applications.
Year
DOI
Venue
2020
10.1109/ASP-DAC47756.2020.9045150
2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC)
Keywords
DocType
ISSN
Ferroelectric,HfO2,Nonvolatile Memory,Synaptic Weight Cell,In-Memory Computing,Neuron
Conference
2153-6961
ISBN
Citations 
PageRank 
978-1-7281-4124-4
0
0.34
References 
Authors
4
3
Name
Order
Citations
PageRank
Kai Ni162.93
Sourav Dutta212.39
Suman Datta341551.93