To lower the barrier to diffractive optical neural networks (DONNs) design, exploration, and deployment, we propose LightRidge, the first end-to-end optical ML compilation framework, which consists of (1) precise and differentiable optical physics kernels that enable complete explorations of DONNs architectures, (2) optical physics computation kernel acceleration that significantly reduces the runtime cost in training, emulation, and deployment of DONNs, and (3) versatile and flexible optical system modeling and user-friendly domain-specific-language (DSL). As a result, LightRidge framework enables efficient end-to-end design and deployment of DONNs, and significantly reduces the efforts for programming, hardware-software codesign, and chip integration. Our results are experimentally conducted with physical optical systems, where we demonstrate: (1) the optical physics kernels precisely correlated to low-level physics and systems, (2) significant speedups in runtime with physics-aware emulation workloads compared to the state-of-the-art commercial system, (3) effective architectural design space exploration verified by the hardware prototype and on-chip integration case study, and (4) novel DONN design principles including successful demonstrations of advanced image classification and image segmentation task using DONNs architecture and topology.

Field-Effect Transistors (FETs) with Three Independent Gates (TIG) can achieve different modes of operation according to the bias of the gate terminals. In particular, TIG FETs were recently shown capable of (i) device-level polarity control, (ii) dynamic threshold modulation and (iii) subthreshold slope tuning down to ultra-steep-slope operation. Experimentally demonstrated using both contemporary FinFETs and emerging silicon nanowires channel technologies, TIGFETs unlock several design opportunities. In this paper, we comment on the digital, analog and RF design capabilities offered by this new class of transistors.

In this paper, we examine graphene as a material for reconfigurable terahertz (THz) optoelectronics. The ability of electrically tuning its optical properties in a wide range of THz frequencies, together with its 2-D nature and facile integration, leads to unique opportunities for inventing novel THz devices as well as for extending the performance of existing THz technologies. We first review progress in graphene THz active optoelectronic components to date, including large-area graphene, plasmonic, and metamaterial-based devices. Advanced designs and associated challenges are then discussed.