Search

Monolithic 3D stacking of complementary FET (CFET) SRAM arrays increases integration density multi-fold while supporting the inherent SRAM advantages of low write power and near-infinite endurance. We propose stacking multiple 8-transistor CFET-SRAM layers on regular CMOS periphery to achieve an ultra-high-density array for computing-in-memory (CIM). CFET and regular CMOS (FinFET) devices are measured and calibrated with BSIM-CMG compact model. SPICE simulations are performed to evaluate the delay of CIM operation, power consumption, and analog computational error due to device non-linearity. The impact of device non-linearity on neural network inference accuracy is evaluated using the CIMulator simulation platform. Lower CFET current drive due to amorphous (deposited) silicon channel is shown to have negligible impact on CIM operational delay in many cases, as the maximum allowable current is limited by wiring resistance, not transistor drive strength while maintaining accurate weighted sum. Compared to regular 2D CMOS FinFET array. CFET SRAM cells show an improvement up to 57.19% in TOPS/W. Furthermore, the performance in TOPS/W mm 2 is improved up to $19\times $ . A factor proportional to the number of stacked layers for monolithically stacked CFET SRAM cells, makes it highly promising for future edge intelligence.

This work presents 2-bits/cell operation in deeply scaled ferroelectric finFETs (Fe-finFET) with a 1 µs write pulse of maximum ±5 V amplitude and WRITE endurance above 109 cycles. Fe-finFET devices with single and multiple fins have been fabricated on an SOI wafer using a gate first process, with gate lengths down to 70 nm and fin width 20 nm. Extrapolated retention above 10 years also ensures stable inference operation for 10 years without any need for re-training. Statistical modeling of device-to-device and cycle-to-cycle variation is performed based on measured data and applied to neural network simulations using the CIMulator software platform. Stochastic device-to-device variation is mainly compensated during online training and has virtually no impact on training accuracy. On the other hand, stochastic cycle-to-cycle threshold voltage variation up to 400 mV can be tolerated for MNIST handwritten digits recognition. A substantial inference accuracy drop with systematic retention degradation was observed in analog neural networks. However, quaternary neural networks (QNNs) and binary neural networks (BNNs) with Fe-finFETs as synaptic devices demonstrated excellent immunity toward the cumulative impact of stochastic and systematic variations.

In this study, ferroelectric FETs (FeFETs) and CMOS inverters are fabricated and analyzed, exhibiting 13% of 593 devices with sub-60 mV subthreshold swing (SS) at room temperature. Forming gas annealing (FGA) is found to not only enhance ferroelectricity but also significantly improve FeFET electrostatics. The experimental results indicate that FeFET with a narrow width shows weaker ferroelectric properties, and SS of sub-60 mV/dec with ID change less than two orders of magnitude. However, FeFET with a broad channel width reveals stronger ferroelectric properties, and SS of sub-60 mV/dec is over 2 orders of magnitude of Id. Finally, typical voltage transfer characteristics (VTCs) of a FeFET CMOS inverter with double sweeps at various VD from 0.6 to 2 V are demonstrated. The results show that hysteresis in a FeFET CMOS inverter could have both clockwise (CW) and counter-clockwise (CCW) loops.