Abstract:
The present disclosure is directed towards the transmission of data and/or power using nanophotonic elements. For example, in one embodiment, a medical imaging system is provided. The imaging system includes a multiplexed photonic data transfer system having an optical modulator configured to receive an electrical signal representative of a set of data and being operable to modulate a subset of photons defined by time, wavelength, or polarization contained within a beam of light so as to encode the photons with the set of data to produce encoded photons, an optical waveguide interfacing with at least a portion of the optical modulator and configured to transmit the beam of light so as to allow the photons to be modulated by the optical modulator, an optical resonator in communication with the optical waveguide and configured to remove the encoded photons from the beam of light, and a transducer optically connected to the optical resonator and configured to convert the encoded photons into the electrical signal representative of the set of data.
Abstract:
Novel integrated electro-optic structures such as modulators and switches and methods for fabrication of the same are disclosed in a variety of embodiments. In an illustrative embodiment, a device includes a substrate with a waveguide and an optical resonator comprising polycrystalline silicon positioned on the substrate. First and second doped semiconducting regions also comprise polycrystalline silicon and are positioned proximate to the first optical resonator. The first optical resonator is communicatively coupled to the waveguide.
Abstract:
A doping profile for a modulator facilitates rapidly changing the carrier density in a waveguide. The carrier density change causes rapid changes in the index of refraction of the waveguide. Example modulators include a ring modulator and a Mach Zender modulator. A charge reciprocating section may be provided to control the amount of injected charge.
Abstract:
Magnetoelectric spin-orbit logic (MESO) devices comprise a magnetoelectric switch capacitor coupled to a spin-orbit coupling structure. The logic state of the MESO device is represented by the magnetization orientation of the ferromagnet of the magnetoelectric switch capacitor and the spin-orbit coupling structure converts the magnetization orientation of the ferromagnet to an output current. MESO devices in which all or at least some of the constituent layers of the device are perovskite materials can provide advantages such as improved control over the manufacturing of MESO devices and high quality interfaces between MESO layers due to the lattice matching of perovskite materials.
Abstract:
Embodiments herein describe techniques for a semiconductor device including a RRAM memory cell. The RRAM memory cell includes a substrate, a RRAM storage cell above the substrate, and a diode adjacent to the RRAM storage cell. The RRAM storage cell includes a first electrode located in a first metal layer above the substrate, a resistive switching material layer adjacent to the first electrode, and a second electrode adjacent to the resistive switching material layer. The second electrode is shared between the RRAM storage cell and the diode. The diode includes the second electrode shared with the RRAM storage cell, a semiconductor layer adjacent to the second electrode, and a third electrode located in a second metal layer above the substrate. Other embodiments may be described and/or claimed.
Abstract:
Techniques and mechanisms for configuring a memory device to perform a sequence of in-memory computations. In an embodiment, a memory device includes a memory array and circuitry, coupled thereto, to perform data computations based on the data stored at the memory array. Based on instructions received at the memory device, control circuitry is configured to enable an automatic performance of a sequence of operations. In another embodiment, the memory device is coupled in an in-series arrangement of other memory devices to provide a pipeline circuit architecture. The memory devices each function as a respective stage of the pipeline circuit architecture, where the stages each perform respective in-memory computations. Some or all such stages each provide a different respective layer of a neural network.
Abstract:
The present disclosure is directed to systems and methods of implementing an analog neural network using a pipelined SRAM architecture (“PISA”) circuitry disposed in on-chip processor memory circuitry. The on-chip processor memory circuitry may include processor last level cache (LLC) circuitry. One or more physical parameters, such as a stored charge or voltage, may be used to permit the generation of an in-memory analog output using a SRAM array. The generation of an in-memory analog output using only word-line and bit-line capabilities beneficially increases the computational density of the PISA circuit without increasing power requirements. Thus, the systems and methods described herein beneficially leverage the existing capabilities of on-chip SRAM processor memory circuitry to perform a relatively large number of analog vector/tensor calculations associated with execution of a neural network, such as a recurrent neural network, without burdening the processor circuitry and without significant impact to the processor power requirements.
Abstract:
A synchronizable optomechanical oscillator (OMO) network including at least two dissimilar silicon nitride (Si3N4) optomechanical resonators that can be excited to evolve into self-sustaining optomechanical oscillators (OMOs) coupled only through an optical radiation field. The tunability of the optical coupling between the oscillators enables one to externally control the dynamics and switch between coupled and individual oscillation states.
Abstract:
Described are apparatus and method for simulating spintronic integrated circuit (SPINIC), the method comprising: generating a spin netlist indicating connections of spin nodes of spin circuits and nodes of general circuits; and modifying a modified nodal analysis (MNA) matrix for general circuits to generate a spin MNA matrix for solving spin circuits and general circuits of the spin netlist.
Abstract:
A system includes a processor and a phased array, coupled to the processor, having an arrayed waveguide for acoustic waves to enable directional sound communication.