Ferroelectric Synapses in Neuromorphic Circuits—Integration of Perovskite- and Hafnia-Based Crossbars

Training neural networks nowadays demands a large time and energy budget, slowing the spread of so-called “neuromorphic computing”. Efforts have been put in developing bio-inspired devices supporting neuromorphic computers, targeting a nano-sized (5x50x50 nm³), low-power (~20 W/petaflop), non-volatile (&gt;1 year), fast (100 ns set/read pulses) and analog (&gt;5 bits) memory. In Mbit arrays, such devices will co-locate storage and computing. Today’s options rely on ion-motion (e.g. red-ox reactions or phase change materials) with intrinsic limitations in terms of endurance and stochasticity. In contrast, the ferroelectric memristor is a purely electronic concept.<br/>In this talk, we present integration schemes for crossbar arrays based on two ferroelectric memristors technology. The first one is based on epitaxial (BiFeO₃) on an oxide electrode (Ca_0.96Ce_0.04MnO₃), grown on 1x1cm² single crystal substrates (YAlO₃). The synaptic functionality of such heterostructure was demonstrated earlier using simple nanocapacitors (shared bottom electrode)^[1]. The second technology is on based polycrystalline HfZrO₄, also on an oxide electrode (WO_x), but directly integrated on Silicium. It follows the Back-End-Of-Line compatible process-flow proposed by Bégon-Lours <i>et al</i>.^[2]. Passive crossbar arrays are fabricated for both technologies, with different constraints on the processing conditions.<br/>The dynamics and the synaptic behavior of the devices are presented, and the functionality of small-scale cross-bar arrays are compared for both technologies. The memristors have comparable On/Off ratio (5-10) and resistance ranges (10-100 MOhms), although their footprint differ by two orders of magnitude. They both show gradual, long-term plasticity upon the application of pulses of increasing amplitude: despite a similar film thickness (~4 nm), the voltage required to operate the hafnia devices is 2V, compared to 5 to 8V for the perovskite. The conduction mechanisms across the ferroelectric thin films are interpreted from temperature dependent measurements. The reliability is also different, with a limited effect of fatigue and retention on the HfZrO₄devices^[3], but a relatively strong aging effect on the BiFeO₃.<br/>Remarkably, the BiFeO₃ thin films have a single crystalline orientation, whereas the hafnia film is polycrystalline. The texture affects the coercive field distribution, with consequences on the multi-level functionality and on the cross-talk in passive crossbars. The prospects of these technologies for neuromorphic computing are discussed: if epitaxial perovskites are promising for unsupervised learning schemes in a passive crossbar array configuration, the back-end compatibility of hafnia synaptic weights offers the possibility of using selectors, with excellent predicted accuracy in tasks such as pattern recognition^[4].<br/>[1] H. Yamada, V. Garcia, S. Fusil, S. Boyn, M. Marinova, A. Gloter, S. Xavier, J. Grollier, E. Jacquet, C. Carrétéro, C. Deranlot, M. Bibes, A. Barthélémy, <i>ACS Nano</i> <b>2013</b>, <i>7</i>, 5385.<br/>[2] L. Begon-Lours, M. Halter, Y. Popoff, Z. Yu, D. F. Falcone, D. Davila, V. Bragaglia, A. La Porta, D. Jubin, J. Fompeyrine, B. J. Offrein, <i>IEEE J. Electron Devices Soc.</i> <b>2021</b>, <i>9</i>, 1275.<br/>[3] L. Bégon-Lours, M. Halter, M. Sousa, Y. Popoff, D. D. Pineda, D. F. Falcone, Z. Yu, S. Reidt, L. Benatti, F. M. Puglisi, B. Offrein, <i>Neuromorphic Comput. Eng.</i> <b>2022</b>, <i>2</i>, DOI 10.1088/2634-4386/ac5b2d.<br/>[4] L. Bégon-Lours, M. Halter, F. M. Puglisi, L. Benatti, D. F. Falcone, Y. Popoff, D. D. Pineda, M. Sousa, B. J. Offrein, <i>Adv. Electron. Mater.</i> <b>2022</b>, 2101395.<br/><br/>This work is supported by FREEMIND (840903), BeFerroSynaptic (871737), ULPEC (732642), CHIST-ERA, UNICO (No. 20CH21-186952) and the BRNC.