Journal of Low Power Electronics and Applications

Accurate branch prediction is crucial for achieving high instruction throughput and minimizing control hazards in modern pipelines. This paper presents a novel LXOR (Local eXclusive-OR) branch predictor, which enhances prediction accuracy while reducing hardware complexity and memory usage. Unlike traditional predictors (GAg, GAp, PAg, PAp, Gshare, Gselect) that rely on large Pattern History Tables (PHTs) or intricate global/local history combinations, the LXOR predictor employs complemented local history and XOR-based indexing, optimizing table access and reducing aliasing. Implemented and evaluated using the MARSS-RISCV simulator on a 64-bit in-order RISC-V core, the LXOR’s performance was compared against traditional predictors using Coremark and SPEC CPU2017 benchmarks. The LXOR consistently achieved competitive results, with a prediction accuracy of up to 83.92%, lower misprediction rates, and instruction flushes as low as 5.83%. It also attained an IPC rate of up to 0.83, all while maintaining a compact memory footprint of approximately 2 KB, significantly smaller than current alternatives. These findings demonstrate that the LXOR predictor not only matches the performance of more complex predictors but does so with less memory and logic overhead, making it ideal for embedded systems, low-power RISC-V processors, and resource-constrained IoT and edge devices. By balancing prediction accuracy with simplicity, the LXOR offers a scalable and cost-effective solution for next-generation microprocessors.

Image convolution is a commonly required task in machine vision and Convolution Neural Networks (CNNs). Due to the large data movement required, image convolution can benefit greatly from in-memory computing. However, image convolution is very computationally intensive, requiring Inner Product (IP) computations for convolution of a $n\times n$ image with a $k\times k$ kernel. For example, for a convolution of a 224 × 224 image with a 3 × 3 kernel, 49,284 IPs need to be computed, where each IP requires nine multiplications and eight additions. This is a major hurdle for in-memory implementation because in-memory adders and multipliers are extremely slow compared to CMOS multipliers. In this work, we revive an old technique called ‘Distributed Arithmetic’ and judiciously apply it to perform image convolution in memory without area-intensive hard-wired multipliers. Distributed arithmetic performs multiplication using shift-and-add operations, and they are implemented using CMOS circuits in the periphery of ReRAM memory. Compared to Google’s TPU, our in-memory architecture requires 56× less energy while incurring 24× more latency for convolution of a 224 × 224 image with a 3 × 3 filter.

Neuromorphic circuits emulate the brain’s massively parallel, energy-efficient, and robust information processing by reproducing the behavior of neurons and synapses in dense networks. Memristive technologies have emerged as key enablers of such systems, offering compact and low-power implementations. In particular, locally active memristors (LAMs), with their ability to amplify small perturbations within a locally active domain to generate action potential-like responses, provide powerful building blocks for neuromorphic circuits and offer new perspectives on the mechanisms underlying neuronal firing dynamics. This paper introduces a novel second-order locally active memristor (LAM) governed by two coupled state variables, enabling richer nonlinear dynamics compared to conventional first-order devices. Even when the capacitances controlling the states are equal, the device retains two independent memory states, which broaden the design space for hysteresis tuning and allow flexible modulation of the current–voltage response. The second-order LAM is then integrated into a FitzHugh–Nagumo neuron circuit. The proposed circuit exhibits oscillatory firing behavior under specific parameter regimes and is further investigated under both DC and AC external stimulation. A comprehensive analysis of its equilibrium points is provided, followed by bifurcation diagrams and Lyapunov exponent spectra for key system parameters, revealing distinct regions of periodic, chaotic, and quasi-periodic dynamics. Representative time-domain patterns corresponding to these regimes are also presented, highlighting the circuit’s ability to reproduce a rich variety of neuronal firing behaviors. Finally, two unknown system parameters are estimated using the Aquila Optimization algorithm, with a cost function based on the system’s return map. Simulation results confirm the algorithm’s efficiency in parameter estimation.