Search

Photonics offers a transformative approach to artificial intelligence (AI) and neuromorphic computing by enabling low-latency, high-speed, and energy-efficient computations. However, conventional photonic tensor cores face significant challenges in constructing large-scale photonic neuromorphic networks. Here, we propose a fully integrated photonic tensor core, consisting of only two thin-film lithium niobate (TFLN) modulators, a III-V laser, and a charge-integration photoreceiver. Despite its simple architecture, it is capable of implementing an entire layer of a neural network with a computational speed of 120 GOPS, while also allowing flexible adjustment of the number of inputs (fan-in) and outputs (fan-out). Our tensor core supports rapid in-situ training with a weight update speed of 60 GHz. Furthermore, it successfully classifies (supervised learning) and clusters (unsupervised learning) 112 × 112-pixel images through in-situ training. To enable in-situ training for clustering AI tasks, we offer a solution for performing multiplications between two negative numbers. The authors showcase a photonic tensor core in TFLN platform that achieves a computational speed of 120 GOPS for neural networks, with capabilities of in-situ training that support exciting prospects of negative number multiplication. The tensor core can efficiently process 112 × 112-pixel images, potentially scaling up AI tasks and offering nanosecond latency without needing a digital processor. [ABSTRACT FROM AUTHOR]

One of the significant challenges in neuromorphic photonic architectures is the lack of good tools to simulate large-scale photonic integrated circuits. It is crucial to perform simulations on a single platform to capture the circuit's behavior in the presence of both optical and electrical components. Here, we adopted a Verilog-A based approach to model neuromorphic photonic circuits by considering both the electrical and optical properties. Verilog-A models for the primary optical devices, such as lasers, couplers, waveguides, phase shifters, and photodetectors, are discussed, along with studying the composite devices such as microring resonators. Model parameters for different optical devices are extracted and tuned by analyzing the measured data. The simulated and experimental results are also compared for validation of Verilog-A models. Finally, a single photonic neuron circuit is simulated by implementing input, weight, and non-linear activation function by using lasers, microring resonators, and modulator, respectively. Electro-optical rapid co-simulation would significantly improve the efficiency of optimizing the devices and provide an accurate simulation of the circuit performance. [ABSTRACT FROM AUTHOR]

In this article, a low phase noise quadrature VCO (QVCO) is proposed, which uses superharmonic injection and current reuse techniques to reduce phase-noise and power consumption. The LC tank circuit quality factor is improved, using a negative resistance. PMOS transistors have also been used instead of NMOS transistors. As a result of these modifications, further phase noise reduction is achieved. The QVCO consists of a VCO operating at 2ω0 (twice the operating frequency) injecting its output signal into the common source nodes of two other oscillators operating at ω0. Using this superharmonic injection technique, in addition to phase noise reduction, the chance of injection pulling caused by powerful PA signals is reduced. Also, the current reuse technique automatically adapts its voltage to the requirement of the supplied stages, therefore, it is not limiting the VCO output swing. Designed for the 900 MHz band and simulated in a 0.18 µm CMOS technology with 1.8 V power supply, the circuit achieves a phase noise of − 141.5 dBc/Hz at 1 MHz offset frequency, while consuming 12.8 mW power. The proposed circuit is compared with several re-simulated previously published work. The comparison shows 17.5 dB reduction in phase noise compared to conventional P-QVCO, while consuming the same amount of power. [ABSTRACT FROM AUTHOR]