368 results about "Optical computing" patented technology

The invention belongs to the technical field of micro-nano photoelectrons, and particularly relates to a multi-channel switchable holographic metasurface encryption device and method. The holographic metasurface encryption device is an array formed by nanoscale structure units through two-dimensional periodic continuation, and is called as a phase change dynamic holographic metasurface. Wherein the structural unit is formed by sequentially overlapping a phase change material layer and a metal material layer on a substrate; rectangular holes are formed in the central parts of the phase change material layer and the metal material layer; holographic encryption is realized by utilizing the adjusting capability of the phase change material unit, a plurality of independent holographic image channels are expanded by utilizing the independence of left and right polarization of circularly polarized light, and the switching function of the metasurface holographic display channel is realized through the phase change degree of the phase change material. The phase-change material is introduced into metasurface holographic display, switching of different responses to incident light is achieved through thermal modulation or electric pulse modulation, and therefore different encryption degrees are achieved. The device has a wide application prospect in the fields of optical display, optical calculation and the like.

The invention provides a spatial light modulator, a self-checking device thereof and a light computing device, and relates to the technical field of optical modulation.The spatial light modulator comprises an incident waveguide structure, a covering plate, a liquid crystal layer, a substrate and an emergent waveguide structure; the incident waveguide structure is optically coupled with the cover plate and is used for guiding externally incident laser into the cover plate at a preset angle; the covering plate is used for enabling laser to be propagated in the covering plate in a total reflection form; the substrate bears the liquid crystal layer, integrates the driving circuit and is used for applying regulation and control voltage to the liquid crystal layer; the liquid crystal layer is arranged on the lower side of the covering plate and used for conducting phase modulation on the laser transmitted to the liquid crystal layer in a total reflection mode in response to the regulation voltage. And the emergent waveguide structure is optically coupled with the covering plate and is used for guiding the laser modulated by the liquid crystal layer out of the covering plate to a free space. According to the spatial light modulator, efficient spatial modulation and accurate control of the light field are realized, so that the integration and function accuracy of the spatial light modulator in self-inspection and light calculation are improved.

The invention discloses an end-to-end optical computing chip based on multi-mode analog signal fusion processing, and belongs to the optical computing technology. Comprising a multi-mode input fusion front-end module, an optical fiber input interface and an end-to-end reasoning module. The multi-mode input fusion front-end module can convert different types of original analog signals such as images, spectrums and radio frequencies into unified broadband spectrum input signals. The end-to-end reasoning module constructs a deep optical neural network, and the deep optical neural network comprises a sensing-convolution integrated unit realized by an arrayed waveguide grating (AWG). The end-to-end reasoning module further comprises a photoelectric non-linear-pooling integrated unit, the average pooling function and the non-linear activation function are achieved at the same time, and light path loss is effectively compensated through injection of the supply light source. And finally, integrating the signals subjected to multi-layer processing by a full connection layer, and outputting a classification result by an output layer. According to the chip architecture, direct and efficient processing of multi-mode analog signals is realized.

Apparatuses, systems and methods for all-optical computing are disclosed. An optical computing apparatus includes a nonlinear optical crystal, at least one light source, and a detector. The at least one light source is configured to spatially modulate vectors of operand values onto coherent optical radiation and to direct the spatially modulated coherent optical radiation into the nonlinear optical crystal, thereby exciting propagating modes in the nonlinear optical crystal corresponding to a computational result of linear and nonlinear operations performed over the vectors. The detector is coupled to receive and sense the coherent optical radiation that has propagated through the nonlinear optical crystal so as to decode the computational result.

The invention discloses an optical computing array based on micro-ring resonators without a free spectral range, which comprises an on-chip wavelength division multiplexing beam splitting array, an on-chip intensity modulation array, two groups of on-chip wavelength division multiplexing beam combining arrays and an on-chip balance detector, the on-chip wavelength division multiplexing beam splitting array and the on-chip wavelength division multiplexing beam combining array are respectively composed of a group of multiple FSR-free MRRs which share the same bus optical waveguide, each resonator corresponds to an independent wavelength channel, and the on-chip intensity modulator array is composed of a plurality of groups of on-chip MZI modulator arrays. According to the optical calculation array implementation method, independent control and coding calculation of different wavelength channels in a broadband wavelength range are realized by utilizing the single harmonic peak characteristic of the FSR-free MRR array and the wide-spectrum intensity modulation function of the MZI unit, the limitation of a free spectrum range on the optical calculation wavelength channel is eliminated, the higher wavelength parallelism is achieved, and the optical calculation array implementation method has the advantages of being simple in structure and convenient to implement. And therefore, the calculation scale is remarkably improved.

The invention discloses an all-optical vortex beam orbital angular momentum mode identification method and system, and relates to the field of optical information processing and optical computing, and the method comprises the steps: S1, constructing a multi-layer architecture all-optical diffraction network; s2, dividing the output detection surface after the diffraction network into a plurality of preset space regions; s3, the vortex light beams carrying orbital angular momentum OAM information sequentially penetrate through the all-optical diffraction network, spatial evolution of a light field in the propagation process is completed, and vortex light classified according to intensity distribution is output; s4, mapping the topological charges of the vortex light to different sub-regions of the detection surface in an intensity distribution form; and S5, performing intensity acquisition on each area on the detection surface through a detector, and determining an OAM mode type of the input light field based on the mode number corresponding to the area with the maximum light intensity. The method is used for performing high-robustness identification on the orbital angular momentum vortex light mode of the vortex light in the presence of a random phase scattering medium.

The invention discloses a dielectric metasurface optical edge detection device and method based on dual-polarization-state Mie resonance, the method shows a non-local dielectric metasurface which is high in robustness and easy to prepare, and the device can achieve polarization-independent edge detection with excellent efficiency and high numerical aperture (NA). By simultaneously utilizing Mie resonance in the s polarization state and the p polarization state, isotropic two-dimensional second-order differential operation under any polarization condition (including non-polarization illumination) is realized. According to the design scheme, real-time image edge extraction can be achieved, the average peak efficiency reaches 30%, the working bandwidth of 40 nm is achieved at the center wavelength of 1064 nm, and high-quality edge detection can be kept under the numerical aperture of 0.5. The work provides a new method for realizing polarization-independent edge detection, and paves a way for practical application of an optical calculation and imaging system.

The invention discloses an optical computing system, a data processing method, a product, equipment and a medium, and relates to the technical field of optical computation.The method comprises the steps that two input and output modules and an optical computing module are arranged, a parameter matrix in the optical computing module is updated according to a to-be-processed feature matrix, and in each iteration, the parameter matrix of the optical computing module is updated; the optical signal modulated by the first input and output module is positively input to the optical calculation module and calculated with the parameter matrix, and the optical signal modulated by the second input and output module is reversely input to the optical calculation module and calculated with a transpose matrix of the parameter matrix, so that an output vector of current iteration is obtained; the key feature information of the feature matrix is determined according to the output vector obtained by the last iteration at the end of iteration, so that the problems of high processing complexity and low processing efficiency caused by processing data through electric calculation are solved, efficient calculation of the parameter matrix and the transpose matrix is completed through optical calculation, the processing complexity is reduced, and the processing efficiency is improved. And the treatment efficiency is improved.

The invention belongs to the technical field of optical calculation, and discloses an error-adaptive optical diffraction neural network in-situ training method, which comprises the following steps: based on the phase of each phase modulation layer, calculating the light field complex amplitude Uk of the input sample complex amplitude on the rear surface of each phase modulation layer and the light field complex amplitude Uo of the input sample complex amplitude on an output plane after forward propagation; calculating an error light field P based on Uo, carrying out three-dimensional central symmetry on a back propagation light path of the error light field P without changing the phase distribution of each phase modulation layer, and calculating the light field complex amplitude of the complex amplitude of the symmetrical error light field on the front surface of each phase modulation layer after forward propagation; the method comprises the steps of obtaining the light field complex amplitude Un + 1-k'of P back propagation to the rear surface of each phase modulation layer, calculating the gradient related to a loss function based on Uk and Un + 1-k 'so as to carry out updating, and carrying out the next round of training until a preset training round or loss convergence is reached. The method can adapt to errors existing in an optical system.

The invention relates to the technical field of optical computing, and discloses an optical neural network and an implementation method thereof, and an optical neural network chip, and the method comprises the steps: an input layer converts and processes an input external signal, obtains an optical signal, and inputs the optical signal to a hidden layer; according to the task requirement of an external signal, the hidden layer dynamically adjusts the weight parameter of the optical neural network under the external magnetic field control condition; an optical signal output by the hidden layer is transmitted to the nonlinear activation layer; aiming at the task requirement of an external signal, the nonlinear activation layer dynamically adjusts the nonlinear characteristic of an activation function under an external magnetic field control condition; and the output layer converts the optical signal output by the nonlinear activation layer into an electric signal, carries out corresponding processing, and outputs a final result. Therefore, the optical neural network is endowed with dynamic adjustability and rapid adjustment capability among different network layers, the weight parameter and the nonlinear function of the full-optical domain dynamic adjustment optical neural network are realized, and the overall operation efficiency is improved.

The embodiment of the invention provides a photoelectric Transform accelerator cooperation method and device, and aims to efficiently process Transform model calculation. Firstly, according to the size M of an optical chip static random access memory on an optical computing chip and feature dimensions d of a query matrix Q, a key matrix K and a value matrix V, Q is divided into Tr sub-blocks, and K and V are respectively divided into Tc sub-blocks. Then, the universal computing chip and the optical computing chip are in interactive communication, the jth sub-block of K and V is transmitted to the optical computing chip firstly, and then the ith sub-block of Q is transmitted circularly for the sub-block. The optical computing chip computes a local attention score matrix Sij and then transmits the matrix back, the general computing chip carries out nonlinear processing on the matrix to obtain a local attention weight matrix Pij, the maximum value mij of each row of the Sij and the sum lij of each row of the Pij are computed, and m, l and O are updated until all sub-blocks K and V are processed. According to the method, through photoelectric collaboration and block calculation, resource utilization is optimized, and calculation efficiency is improved.

The present disclosure relates to the technical field of optical computing, and particularly relates to an intelligent optical computing chip cluster architecture and system. The architecture comprises: a plurality of optical computing chips, and optical path channels are established between the plurality of optical computing chips by using spatial phase adjustment to modulate light beams; and high-speed optical communication and optical diffraction network computing are performed between the plurality of optical computing chips by performing time-domain intensity modulation on the optical path channels. The present disclosure adopting the above scheme can realize the interconnection computing of optical computing chips in the spatial dimension, and does not rely on electricity for information transmission.

The present invention provides a method for optimizing a neural network model in optical computing. The method comprises: acquiring an initial quantization scaling coefficient and an optical computing system noise suppression coefficient; adjusting the initial quantization coefficient on the basis of the noise suppression coefficient; and then using the adjusted coefficient to quantize a neural network model. The present invention improves the stability and reliability of a model in an optical computing system, thereby reducing the impact of noise of the optical computing system on a neural network model.

The invention provides an optical signal synchronous calibration device and method of an optical computing system. The device comprises an optical probe array, an AI coprocessor, an optical path tuning engine and a low-speed electric feedback line, wherein the optical probe array is arranged on a chip; the optical probe array detects optical signals of wavelength channels corresponding to the plurality of optical calculation units and converts the optical signals into electric signals; the AI coprocessor drives a corresponding optical calculation unit to emit a detection pulse according to a pre-distributed time slot index variable, extracts a phase error from the electric signal and calculates a final calibration amount based on the phase error; the optical path tuning engine performs an optical path tuning operation based on the final calibration amount to calibrate an error of the corresponding optical calculation unit; and the low-speed electric feedback line transmits the electric signal to the AI coprocessor and transmits the detection pulse to the chip. According to the invention, through cooperation of spatial distributed detection and board-level centralized processing, real-time calibration in a dynamic environment is realized.

The present invention discloses a reconfigurable integrated optical computing core model, comprising: M×N matrix calculation units; each matrix calculation unit includes two dual-waveguide microring resonators, a straight waveguide, and a phase change material heater, and the straight waveguide is made by covering a phase change material on a silicon waveguide; the phase change material heater is used to heat the phase change material to generate a phase change, thereby changing the light absorption of the straight waveguide; the integrated optical computing core model realizes the multiplication operation of an M×N matrix and an N×1 vector through integrated optical methods, where M and N are natural numbers. The present invention uses a phase change material in the computing core, changes the phase state of the phase change material by heating, changes the light absorption of the straight waveguide, and further changes the matrix elements in the computing core, realizing the reconfigurable characteristics of the computing core model. The present invention can be widely applied to the field of integrated optics.

The present invention belongs to the technical field of semiconductor optoelectronic devices, and specifically relates to an optical computing array based on a germanium modulator, comprising a cross matrix, wherein the cross matrix is ​​formed by crossing multiple rows of mutually parallel input optical waveguides and multiple columns of mutually parallel output optical waveguides; and a photodetector is provided at the output end of each column of the output optical waveguide; multiple optical splitters; multiple germanium modulators, each of the germanium modulators corresponds to one of the cross waveguides, and the first input end of the germanium modulator is connected to the output end of the optical splitter through a transmission optical waveguide; and multiple optical combiners, each of the optical combiners is respectively connected to the output end of the germanium modulator and the output optical waveguide. Through the above structure, the present application comprehensively provides a computing array with a high responsiveness having a thermal compensation mechanism and capable of reducing light reflection, so as to realize a solution for a low-power large-scale integrated computing array under the condition of frequent switching.

The invention discloses a neural network accelerator based on optical computing, which relates to the technical field of artificial intelligence hardware acceleration and comprises an optical convolution module and an optical full connection module which are directly connected. The optical full connection calculation part can be started after the optical convolution calculation part is completed, photoelectric conversion between convolution and full connection is avoided, photoelectric conversion links are reduced to the maximum extent, the photoelectric conversion loss rate is reduced, and the data transmission efficiency is improved. According to the method, the high parallel characteristic of photonics and the dynamic calculation requirement of a neural network are deeply fused, high-density photon integration is achieved, convolution and full-connection operation are directly completed in an optical domain through the optical calculation technology, the calculation speed and precision are improved, meanwhile, the system energy consumption overhead is reduced, and the system performance is improved. And an efficient and low-power-consumption hardware basis is provided for training and reasoning of a super-large-scale model.

The invention provides a chip package, an optical fiber assembly and optical computing equipment, and the chip package comprises a substrate; the photon integrated circuit chip is provided with a first surface and a second surface opposite to the first surface, and the second surface is used for being fixedly connected with the substrate; the optical fiber assembly comprises an optical fiber bearing plate, a cover plate and an optical fiber located between the optical fiber bearing plate and the cover plate, the optical fiber bearing plate comprises a first area and a second area, the first area is used for bearing the optical fiber, and the second area is fixed to the first surface of the photonic integrated circuit chip; an optical fiber in the optical fiber assembly is coupled to the photonic integrated circuit chip.

An optical computing device includes an optical computing section including a first transmissive optical modulation element having cells each having an independently set phase modulation amount. The first transmissive optical modulation element emits a signal light, in a signal direction, generated when transmitted light beams phase-modulated by the cells interfere with each other and a noise light, in a noise direction, transmitted through the first transmissive optical modulation element without being phase-modulated by the cells. The optical computing device includes an optical sensor that detects the signal light outputted from the optical computing section and generates an electrical signal indicating a result of the detection. The first transmissive optical modulation element is configured such that an impact that the noise light has on the electrical signal is smaller than the impact in a state where the signal direction aligns with the noise direction.

The invention relates to the field of optical computing, and provides a signal processing method and device based on an optical computing chip and a photoelectric fusion computing system.The signal processing device comprises an optical input modulation module, a first weight mapping module, a second weight mapping module and an optical output combining module, and the optical input modulation module converts an input signal into a modulated optical signal; the first weight mapping module obtains a first output optical signal based on the first weight; the second weight mapping module acquires a second output optical signal based on a second weight; the optical output combining module obtains a comprehensive output signal based on the first output optical signal and the second output optical signal; the second weight mapping module comprises a light dimension reduction unit, a low-dimensional light modulation unit and a light dimension raising unit, and the light dimension reduction unit performs low-dimensional projection on a modulated light signal; the low-dimensional optical modulation unit adjusts the second weight based on the second weight update signal and obtains an optical signal after low-dimensional processing; and the light dimension raising unit carries out high-dimensional projection on the light signal after low-dimensional processing.

An optical computing device includes: one or more light-diffraction elements each of which includes microcells, wherein each of the microcells has an individually set thickness or refractive index; and an optical signal input section that simultaneously inputs an optical signal and a delayed optical signal obtained by delaying the optical signal to the one or more light-diffraction elements.

The invention relates to the technical field of vehicle-mounted computing, in particular to a dynamic energy efficiency management and emergency redundancy processing device and method for vehicle-mounted heterogeneous computing, and the device comprises a reconfigurable computing array which is used for carrying out dynamic partitioning and resource scheduling on an FPGA (Field Programmable Gate Array) logic unit; the multi-protocol converged communication panel is used for receiving a plurality of sensor data input into the reconfigurable computing array and carrying out mixed scheduling on the plurality of sensor data; the AI resource scheduling engine is used for redistributing computing power in the reconfigurable computing array according to the biological characteristics and a pre-constructed reinforcement learning dynamic energy efficiency model; and the three-level emergency redundant equipment is used for switching a main power supply, activating a preset optical calculation standby channel and starting V2X point cloud reconstruction when a main calculation unit in the reconfigurable calculation array breaks down so as to release nuclear explosion calculation power. Therefore, the problems of dynamic energy efficiency deficiency, redundancy mechanism insufficiency, multi-sensor conflict and the like of an existing vehicle-mounted computing system are solved.

The embodiment of the invention provides a semiconductor structure, a semiconductor packaging structure and optical computing equipment, and the semiconductor structure comprises a bearing structure which is provided with a first limiting structure on the upper surface; the photonic integrated circuit chip is fixed on the bearing structure, and an optical coupling area is formed at the edge position of one side of the photonic integrated circuit chip; the optical fiber array comprises optical fibers and an optical fiber base used for fixing the optical fibers, a second limiting structure is arranged on the lower surface of the optical fiber base, the first limiting structure and the second limiting structure are used for achieving pluggable connection, and orthographic projections of the optical fibers and the second limiting structure on the lower surface of the optical fiber base have overlapped parts; the lens array comprises lenses, and the lenses are configured to converge light emitted by the optical coupling area into the optical fibers and / or converge light emitted by the optical fibers into the optical coupling area when the optical fiber array is connected to the bearing structure in a pluggable mode. According to the technical scheme provided by the embodiment of the invention, the packaging yield is improved through plugging of the optical fiber array.

The invention discloses a clock control method of a multi-channel driving system for DAC time division multiplexing in an optical computing system, which comprises the following steps: S101, acquiring a time interval from an edge moment when a control signal of a sampling control circuit jumps from an effective state to an invalid state to a stable holding state at an initial temperature; s102, acquiring the time interval of the DAC from the updating of the input data to the stabilization of the analog output voltage of the DAC; s103, target compensation delay needed by DAC input data is obtained, and the target compensation delay meets the requirement that after the control signal enters the invalid state, analog output of the DAC is kept stable and unchanged within the establishment keeping time; and S104, performing delay processing of target compensation delay on the input data of the DAC by using a delay circuit arranged at the input end of the DAC, and inputting the data into the DAC. According to the invention, DAC data updating and the working time sequence of the sampling hold circuit can be coordinated, and sampling errors caused by time sequence conflicts are avoided.

Described herein are embodiments of a photonic computing system comprising one or more processors in communication with disaggregated memory through one or more optical channels. The disaggregated memory comprises multiple memory units placed on a photonic substrate that includes a photonic network that can be programmed to configure which of the memory units can be accessed by each of the processor(s). The disaggregated memory includes a memory controller for reading and writing data to / from the memory units. The memory controller may be configured to perform processing in concert with the processor(s).

The application discloses a vertical micro-mirror structure optical computing chip and a wafer-level intelligent manufacturing method thereof, and relates to the field of optical computing chips.The optical computing chip comprises a plurality of optical modulators and a plurality of quantum logic gates, and the optical modulators are provided with interference light paths based on vertical micro-mirrors, so that optical modulation is realized; the quantum logic gates construct stable light paths through the mirrors provided by the vertical micro-mirrors, realize interference by means of a beam splitter, and perform Hadamard transformation by a wave plate at the entrance or exit of a target light path, so that optical computing is realized; a deep-groove beam splitter or a deep-wall beam splitter is used as the beam splitter, the silicon walls in the deep-wall beam splitter are provided with a predetermined included angle perpendicular to the two side walls of the substrate, and the deep-groove beam splitter is manufactured in the following manner: a deep groove pattern is photoetched on the surface of a single-crystal silicon wafer; the deep groove with the predetermined angle is etched by deep etching and the side walls are smoothed; an optical thin film is deposited in the deep groove; the shape of the deep-groove beam splitter is photoetched and etched by deep etching, and the side walls are smoothed; and an optical antireflection film is grown on the vertical side walls.

The present invention belongs to the technical field, and specifically relates to an optical computing module and an optical computing array, comprising: a cross-arranged input optical waveguide and an electrical bus, the input end of the input optical waveguide being provided with a splitter, the output end of the splitter being connected to the first input end of a photoelectric signal processing unit via a transmission optical waveguide, the output end of the photoelectric signal processing unit being connected to the electrical bus, which is completely different from the discrete optical computing unit scheme in the prior art. The present application adopts an independent photoelectric signal processing unit, which can realize the rapid conversion of unmodulated optical signals into electrical signals, and its volume remains basically unchanged from the size of the detector device in the prior art, thereby making the size of a single optical computing unit smaller, thereby realizing a larger-scale matrix compared to the existing scheme, and avoiding the problem of difficult wiring of existing discrete devices. Its life performance is the same as that of conventional silicon-based devices, and can meet the frequent switching requirements of training levels.

The invention discloses an RRAM optical computing array reading circuit and method, and the circuit comprises an RRAM optical computing array, and a source line of each unit in the RRAM optical computing array is used for inputting a pulse signal to apply voltage bias; the pulse signal generation unit is used for generating a word line control signal and an RRAM optical calculation array unit bias voltage; the analog multiplexing control unit is used for selecting each subunit of the RRAM optical computing array; the pre-amplification and signal conversion unit is provided with a plurality of circuits and is used for detecting current changes of the photoelectric detection array subunits, converting the current changes into 0 / 1 signals and outputting the 0 / 1 signals to the FPGA control unit; the FPGA control unit is a system microcontroller and is used for controlling the pulse signal generation unit and the output analog multiplexer and processing signals of the pre-amplification and signal conversion unit. According to the invention, the circuit conversion problem caused by a large-span conductive state is solved, the circuit area is simplified, the system power consumption is reduced, and the applicability is high.

The invention discloses an optical calculation chip matrix weight control precision measurement and calibration device and method, and the device mainly comprises a photoelectric detector array module which is used for carrying out the photoelectric signal conversion of an optical signal outputted by an optical calculation chip, a parameter extraction and analysis module which is used for collecting an electric signal, and a calibration module. Calculating the matrix weight control precision and the control rate of the optical calculation chip; and the environment compensation and closed-loop control module is used for monitoring the environment temperature of the optical computing chip and performing compensation calibration control on the bias voltage of the optical computing chip based on the change of the temperature so as to realize accurate regulation and control on the matrix weight. According to the device and the method, the matrix weight control precision and the control rate can be accurately measured, external environment change parameters are accurately sensed, voltage parameters in weight control are changed through a compensation algorithm, and high performance and reliable operation of an optical calculation chip are effectively guaranteed.

The invention belongs to the technical field of semiconductor optoelectronic devices, and particularly relates to an optical computing array based on a reverse bias germanium modulator, which comprises a cross matrix formed by crossing a plurality of rows of mutually parallel input optical waveguides and a plurality of columns of mutually parallel output optical waveguides, a photoelectric detector is arranged at the output end of each row of output optical waveguides; a plurality of optical splitters; each germanium modulator corresponds to one crossed waveguide, and the first input end of each germanium modulator is connected with the output end of the optical splitter through a transmission optical waveguide; each light combiner is connected with the output end of the germanium modulator and the output optical waveguide, through the above structure, the computing array which has a thermal compensation mechanism, can reduce light reflection and is high in responsivity is comprehensively provided, and therefore under the condition that frequent switching is met, the computing array has the advantages that the computing efficiency is improved, and the computing efficiency is improved. And a low-power-consumption large-scale integrated calculation array scheme is realized.