On-chip all-optical second-order ordinary differential equation solver based on a single microdisk resonator.

This paper proposes an all-optical second-order ordinary differential equation (SODE) solver based on a single microdisk resonator. We validate the feasibility of our structure for constant and complex coefficient SODE solutions for Gaussian and super-Gaussian pulses. The results demonstrate a good agreement between the solutions obtained with the designed structure and those obtained through mathematical calculations for both constant and complex coefficient SODEs. We also discuss the influence of input optical signal pulse width on solution result deviations. Furthermore, we validate the capability of the designed structure to achieve tunable solutions for complex-coefficient SODEs with a tuning power of less than 10 mW. The device footprint is approximately 20×30 µm2, and it is 3-4 times smaller than the current smallest solving unit. The maximum Q-factor reaches 9.8×104. The proposed device avoids the traditional approach of cascading two resonators for SODE solving. Moreover, achieving mode alignment within the same resonator reduces the process challenges associated with aligning multiple devices in a cascade. Furthermore, it offers wider applicability for solving SODEs, namely, the ability to solve both constant and complex coefficient SODEs with complete derivative terms.

Phase-change material-assisted all-optical temporal differentiator.

This paper proposes a novel microring resonator (MRR)-based all-optical tuning temporal differentiator (DIFF). Specifically, the DIFF uses nonvolatile phase-change material Ge2Sb2Te5 (GST) to achieve low energy consumption and high-speed optical control of the state of the MRR, avoiding the traditional electro-optic (EO) and thermo-optic (TO) tuning designs. By changing the crystallinity of GST to changing the coupling regimes of the MRR, a broad range for the differentiation order α, i.e., 0.47-1.64 can be realized. The intensity response and phase response of the GST-assisted MRR, and normalized intensity in the output of the temporal DIFFs for Gaussian optical pulses have been obtained by simulation. Furthermore, input pulse width and detuning influence on the differentiation order and output deviation are discussed. Finally, our structure can effectively reduce the chip area and power consumption compared with the traditional EO and TO tuning designs.

StarLight: a photonic neural network accelerator featuring a hybrid mode-wavelength division multiplexing and photonic nonvolatile memory.

This paper proposes StarLight, a low-power consumption and high inference throughput photonic artificial neural network (ANN) accelerator featuring the photonic 'in-memory' computing and hybrid mode-wavelength division multiplexing (MDM-WDM) technologies. Specifically, StarLight uses nanophotonic non-volatile memory and passive microring resonators (MRs) to form a photonic dot-produce engine, achieving optical 'in-memory' multiplication operation with near-zero power consumption during the inference phase. Furthermore, we design an on-chip wavelength and mode hybrid multiplexing module and scheme to increase the computational parallelism. As a proof of concept, a 4×4×4 optical computing unit featuring 4-wavelength and 4-mode is simulated with 10 Gbps, 15 Gbps and 20 Gbps data rates. We also implemented a simulation on the Iris dataset classification and achieved an inference accuracy of 96%, which is entirely consistent with the classification accuracy on a 64-bit computer. Therefore, StarLight holds promise for realizing low energy consumption hardware accelerators to address the incoming challenges of data-intensive artificial intelligence (AI) applications.

Experimental demonstration of an intelligent control plane with proactive spectrum defragmentation in SD-EONs.

The cooperation of software-defined networking and flexible grid optical transport technology allows operators to elastically control the network using software running on a network operating system within a centralized way. However, existing approaches dealing with spectrum fragmentation are mostly the reactive strategy, which reconfigures network resources to overcome spectrum fragmentation when the controller detects the fragmentation. In this paper, we focus on how to improve the control plane intelligence of software-defined elastic optical networks (SD-EONs) by using a proactive strategy. More specifically, we design a novel routing, modulation level and spectrum allocation algorithm (RMLSA) based on spectral efficiency and connectivity (SEC) i.e., SEC-RMLSA, in order to improve the utilization efficiency of network resources. Meanwhile, we develop a routing application and an extended OpenFlow protocol to achieve a seamless operation between the controller and the optical data plane. Moreover, all the proposed methodologies are implemented and demonstrated in an SD-EON testbed that has both OpenFlow-based control plane and data plane. Finally, the proposed framework, experimental demonstration, and numerical evaluation are reported for different optical flows. The results show the system's overall feasibility and efficiency.