Wavelength-routed networks-on-chip (WRONoCs) are known for providing high-speed and low-power communication. Despite those advantages, the key components, microring resonators (MRRs), are prone to process and thermal variations, which cause signals to fail to reach their intended destinations. Thus, several WRONoC fault-tolerant methods propose to prepare a constant number of backups, which often leads to inefficient resource allocation, i.e. insufficient backups for the signals that are prone to errors, while more than enough backups for the signals that are barely affected, resulting in much power waste. In this work, we propose a dynamical backup resource allocation method for reliability maximization and power minimization in WRONoCs. Precisely, our method starts with accurately modeling the WRONoC faults, which considers the deviation of an MRR's default behavior as a Gaussian Distribution. Since signal paths consist of different numbers of MRRs, and the signals have different probabilities of deviating from their designated paths, our method customizes the number of backup paths for every signal and automatically allocates the minimum resources to optimize the reliability.

With low latency and collision-free communication, wavelength-routed optical networks-on-chip (WRONoC) become an effective solution to the growing demands for multi-core communications. Microring resonators (MRRs), the primary optical components in WRONoC, are susceptible to process variation. Under process variation, the MRR’s transmission spectrum shifts, results reduced signal power and increased crosstalk. However, the impacts caused by process variation have not yet been considered in WRONoC designs. In this work, we propose a methodology to optimize the MRR radii and signal wavelengths to counter process variation. Specifically, we construct analytical models of expected signal power under MRR process variation and develop optimization methods to maximize the expected signal transmission power in WRONoC. Results show up to 7.51 dB improvement in worst-case expected signal transmission power compared to designs that do not consider process variation.

To meet the increasing demand for high-speed communication in many-cores systems, optical networks-on-chip (ONoCs) have gained attention for their ability to deliver low-latency and high-bandwidth data transmission. As a specific type of ONoCs, wavelength-routed ONoCs (WRONoCs) offer exclusive benefits such as collision-free and arbitration-free communication between cores. To guide the design and optimization of WRONoCs, many simulators have been developed to model WRONoC behavior at the device and circuit levels, offering detailed insights into photonic components. These tools have significantly advanced photonic design. As WRONoCs move closer to practical applications, network-level simulation becomes increasingly important for evaluating end-to-end communication behavior. Despite the need, existing simulators rarely support WRONoC modeling at the network level, leaving a critical gap in current toolchains. To address that, we propose the first network-level WRONoC simulation platform, WROXIM, adapted from an open-source NoC simulator, Noxim. It supports cycle-accurate modeling of optical communication behaviors and retains full compatibility with traditional electrical NoC simulations. To model realistic communication behaviors, WROXIM incorporates both optical and electrical components, including serializers, deserializers, waveguides, buffers, and processing elements (PEs). This modeling approach allows the simulator to capture end-to-end data movement from a PE through the optical interconnect to another PE. Given an application with multiple tasks, WROXIM supports task-driven workloads and provides key performance metrics such as latency, throughput, and energy consumption, offering a platform for design exploration and verification for WRONoCs.

Wavelength-routed optical networks-on-chip (WRONoC) is a promising solution for achieving high-bandwidth, low-power on-chip communications. Previous work has aimed to reduce transmission latency in WRONoC by bandwidth allocation considering application communication demands. This is achieved by optimizing core-to-port mapping and configuring the radii of microring resonators (MRRs), which are the key routing components in WRONoC. However, previous work suffers from slow runtime and limited solution quality and fails to obtain feasible solutions for large applications given WRONoC topology. To address these, we propose a novel graph-based approach, FAB, to fast and efficiently reduce transmission latency in WRONoC. Specifically, we formulate core-to-port mapping and MRR radii configuration as two-stage weighted subgraph matching problems. In each stage, we construct graphs to model the demands or the bandwidth potential between vertices. By introducing strict weight-based matching strategies and progressively relaxing infeasible cases, FAB can quickly achieve optimized high-quality solutions. Experimental results demonstrate that FAB reduces worst-case transmission latency by up to 87.5% and accelerates optimization by up to 500,000× compared to the state-of-the-art method.

Wavelength-routed optical networks-on-chip (WRONoCs) are well-known for providing high-speed and collision-free communication in multi-core processors. Previous work was unable to simultaneously reduce the design complexity and total optical power consumption of WRONoC. Besides, in current designs, each microring resonator (MRR), which is the key component of WRONoC, is configured to demultiplex to one specific wavelength. This significantly increases the MRR usage and the insertion loss. In this work, we adapt different types of ONoC routers into the mesh-based template. To reduce MRR usage, we take advantage of an important feature of MRR, multi-resonance, so that a single MRR can demultiplex signals on multiple wavelengths. To this end, we propose an efficient design method that synthesizes mesh-based WRONoCs using multi-resonance MRRs and existing optical routers to reduce total power consumption. The experimental results show that our method outperforms state-of-the-art design methods in significantly reducing MRR usage and optical power.

With the rapid development of integrated photonic technology, wavelength-routed optical networks-on-chip (WRONoC) is emerging as a high-potential computing architecture due to its low power consumption, high bandwidth, and conflict-free communication advantages. Previous works utilize the multi-resonance properties of the microring resonator (MRR), the key component in WRONoC, to transmit multiple signals on different wavelengths in one transmission path, thereby achieving parallel communication. However, they do not consider the demands of the actual application communication bandwidth. If communications with high bandwidth demands are not allocated with highly parallel transmission paths, they may become the bottleneck of the network, resulting in increased transmission cycles and overall data transmission time. In this work, we propose an optimization strategy that allocates signal wavelengths for each communication based on its actual bandwidth demand to reduce communication time. Specifically, based on the actual bandwidth demands and topology structure, we first map the communication nodes in the target application to the ports of a WRONoC topology. Next, we optimize the radii of MRRs in the topology and allocate the signal wavelengths to each transmission path to minimize the worst-case data transmission cycle. Experimental results show that, compared to methods that only consider communication parallelism, our strategy can reduce the worst-case of data transmission cycles by over five times, thereby significantly decreasing the time required for data transmission.