A Cryogenic Memristive Neural Decoder for Fault-tolerant Quantum Error Correction

Neural decoders for quantum error correction (QEC) rely on neural networks to classify syndromes extracted from error correction codes and find appropriate recovery operators to protect logical information against errors. Despite the good performance of neural decoders, important practical requirements remain to be achieved, such as minimizing the decoding time to meet typical rates of syndrome generation in repeated error correction schemes, and ensuring the scalability of the decoding approach as the code distance increases. Designing a dedicated integrated circuit to perform the decoding task in co-integration with a quantum processor appears necessary to reach these decoding time and scalability requirements, as routing signals in and out of a cryogenic environment to be processed externally leads to unnecessary delays and an eventual wiring bottleneck. In this work, we report the design and performance analysis of a neural decoder inference accelerator based on an in-memory computing (IMC) architecture, where crossbar arrays of resistive memory devices are employed to both store the synaptic weights of the decoder neural network and perform analog matrix-vector multiplications during inference. In proof-of-concept numerical experiments supported by experimental measurements, we investigate the impact of TiO$_\textrm{x}$-based memristive devices' non-idealities on decoding accuracy. Hardware-aware training methods are developed to mitigate the loss in accuracy, allowing the memristive neural decoders to achieve a pseudo-threshold of $9.23\times 10^{-4}$ for the distance-three surface code, whereas the equivalent digital neural decoder achieves a pseudo-threshold of $1.01\times 10^{-3}$. This work provides a pathway to scalable, fast, and low-power cryogenic IMC hardware for integrated QEC.

Hardware-aware Training Techniques for Improving Robustness of Ex-Situ Neural Network Transfer onto Passive TiO2 ReRAM Crossbars

Passive resistive random access memory (ReRAM) crossbar arrays, a promising emerging technology used for analog matrix-vector multiplications, are far superior to their active (1T1R) counterparts in terms of the integration density. However, current transfers of neural network weights into the conductance state of the memory devices in the crossbar architecture are accompanied by significant losses in precision due to hardware variabilities such as sneak path currents, biasing scheme effects and conductance tuning imprecision. In this work, training approaches that adapt techniques such as dropout, the reparametrization trick and regularization to TiO2 crossbar variabilities are proposed in order to generate models that are better adapted to their hardware transfers. The viability of this approach is demonstrated by comparing the outputs and precision of the proposed hardware-aware network with those of a regular fully connected network over a few thousand weight transfers using the half moons dataset in a simulation based on experimental data. For the neural network trained using the proposed hardware-aware method, 79.5% of the test set's data points can be classified with an accuracy of 95% or higher, while only 18.5% of the test set's data points can be classified with this accuracy by the regularly trained neural network.