AUTHOR=Minguet Lopez Joel , Barraud Sylvain , Cooper David , Jannaud Audrey , Grenier Adeline , Souhaité Aurelie , Pedini Jean-Michel , Comboroure Corinne , Gharbi Ahmed , Boulard François , Castan Clément , Lambert Amélie , Andrieu François TITLE=Rethinking 1T1R architecture and OxRAM stack for memristive neural network inference in-memory JOURNAL=Frontiers in Nanotechnology VOLUME=Volume 7 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/nanotechnology/articles/10.3389/fnano.2025.1549547 DOI=10.3389/fnano.2025.1549547 ISSN=2673-3013 ABSTRACT=Neural Network hardware in-memory implementations based on memristive synapses are a promising path towards energy efficient Edge computing. Among others, Oxide-based Resistive Random Access Memory (OxRAMs) devices utilization for synaptic weight hardware implementation has shown promising performance on various types of Neural Networks, notably when coupled with bit-error correcting codes or adaptive programming schemes for the device intrinsic variability management. In this context, memristive footprint reduction coupling with Multi-Level-Cell (MLC) operation remains essential to hardware implement highly accurate state-of-art Neural Networks, whose number of parameters is exponentially increasing over time. In this work, a compact OxRAM-based 1 Transistor – 1 Resistor (1T1R) architecture, where the memory is integrated inside the 40 nm × 40 nm drain contact of thin-gate oxide FDSOI transistors, is demonstrated in 28 nm technology. The memory structure is optimized from the OxRAM active material level to the cell architecture. This results in 106 endurance and 11-level MLC encoding resilient to 109 inference cycles compatible with 0.0357 μm2 bitcell footprint potential in 28 nm technology. Altogether, the proposed 1T1R cell density is competitive with respect to ultra-dense 1S1R-based Crossbar arrays, while being compatible with in-memory Neural Network inference implementations on-chip.