CN-115775022-B - Device of optical pulse neural network processor

CN115775022BCN 115775022 BCN115775022 BCN 115775022BCN-115775022-B

Abstract

An optical pulse neural network processor device comprises an SOA and DFB-SA array optical pulse neural network chip which is integrated and packaged in a single mode, a multi-channel tunable light source, a modulator array, a photoelectric detector PD array, a transimpedance amplifier array, an analog-to-digital conversion array, two digital-to-analog conversion arrays, a control circuit array and a memory array. The optical pulse neural network chip uses a semiconductor optical amplifier SOA as a photon synapse and uses a distributed feedback semiconductor laser DFB-SA with a saturated absorption region as a photon neuron. Both photonic synapses and photonic neurons are based on group III/V materials, so the sub-photonic pulse neural network chip can be monolithically integrated. The device ensures that the optical pulse neural network chip can be monolithically integrated and the optical pulse neural network processor can be flexibly configured.

Inventors

XIANG SHUIYING
GAO SHUANG
ZHANG YAHUI

Assignees

西安电子科技大学

Dates

Publication Date: 20260505
Application Date: 20210907

Claims (4)

1. The device of the optical pulse neural network processor comprises an SOA (service oriented architecture) and DFB-SA (distributed feedback-architecture) array optical pulse neural network chip which is monolithically integrated and packaged, a multichannel tunable light source, a modulator array, a photoelectric detector PD (potential difference) array, a transimpedance amplifier array, an analog-to-digital conversion array, two digital-to-analog conversion arrays, a control circuit array and a memory array, and is characterized in that the optical pulse neural network chip is monolithically integrated based on III/V groups, and the output end of the multichannel tunable light source is connected with the optical input end of the modulator array; the output end of the modulator array is respectively connected with the input end of the optical pulse neural network chip, the two output ends of the controller are connected with the input ends of the two digital-to-analog conversion arrays, the output ends of the two digital-to-analog conversion arrays are respectively connected with the radio frequency end of the modulator and the current control end of the optical pulse neural network chip, the output end of the optical pulse neural network chip is connected with the input end of the PD array, the output end of the PD array is connected with the input end of the transimpedance amplifier array, the output end of the transimpedance amplifier array is connected with the input end of the analog-to-digital conversion array, the output end of the analog-to-digital conversion array is connected with the input end of the control circuit, the control circuit is mutually connected with the memory for data storage and reading, and the optical pulse neural network chip is characterized in that, the output end of the modulator is connected with the input end of the on-chip beam splitter, the output end of the beam splitter is connected with the input end of the array waveguide grating, the output end of the array waveguide grating is connected with the input end of the SOA synapse, the output end of the SOA synapse is connected with the input end of the second array waveguide grating, the output end of the second array waveguide grating is connected with the DFB-SA neuron array, and the output of the DFB-SA neuron array is used as the output of the optical pulse neural network chip for next transformation and analysis.
2. The device of claim 1, wherein a semiconductor optical amplifier SOA is used as a photonic synapse, a feedback semiconductor laser DFB-SA with a saturated absorption region is used as a photonic neuron, and the photonic synapse and the photonic neuron are based on III/V materials, so that the optical pulse neural network chip can be monolithically integrated.
3. An optical pulse neural network processor device according to claim 1, wherein the optical pulse neural network processor is flexibly configurable through connection of an optical/electrical interface, a control circuit, etc.
4. The device of claim 1, wherein the number of nodes of the optical impulse neural network chip is scalable to n x n.

Description

Device of optical pulse neural network processor Technical Field An optical pulse neural network processor device belongs to the field of optical calculation and optical signal processing, and particularly relates to an optical pulse neural network processor device based on a semiconductor optical amplifier and a distributed feedback laser with a saturated absorption region. The optical pulse neural network chip is characterized by being based on III/V group monolithic integration. Background In comparison to traditional von neumann computing systems, pulsed neural network computing seeks to obtain inspiration from the abstract principles of biological information processing, designing a scalable and cost-effective hardware system. In tasks involving pattern analysis, decision making, optimization, learning, and real-time control of multi-sensor, multi-actuator systems, neuromorphic architectures have powerful advantages over von neumann architectures in terms of efficiency, fault tolerance, adaptability, etc. The explosive development of optical integration technology has greatly driven high-performance optical computing to become a leading-edge hotspot of the world again. The on-chip optical pulse neural network fully integrates the characteristics of high-speed optical communication, optical interconnection, optical integration and nerve mimicry calculation, and has the advantages of super-high speed, large bandwidth, multiple dimensions and the like. Has wide application prospect in the field of high-performance calculation and artificial intelligence. The basic functional units of the photonic pulse neural network are photonic pulse neurons and photonic synapses. Currently, there is some progress made in optical impulse neural networks based on discrete device photonic impulse neurons and optical synapses, or based on heterogeneous integration. However, monolithically integrated optical impulse neural networks are still in the leading edge discovery stage. There is therefore an urgent need to develop a monolithically integrated optical pulse neural network chip and a processor based on the optical pulse neural network chip. Disclosure of Invention In view of the above-stated deficiencies of the prior art, the present invention is directed to an apparatus for an optical impulse neural network processor. In the device, an optical pulse neural network chip uses a semiconductor optical amplifier SOA as a photon synapse and uses a distributed feedback semiconductor laser DFB-SA with a saturated absorption region as a photon pulse neuron. Both the photon synapse and the photon pulse neuron are based on III/V group materials, so that the photon pulse neural network chip can be monolithically integrated. The object of the present invention is achieved by the following means. An optical pulse neural network processor device comprises an SOA and DFB-SA array optical pulse neural network chip which is integrated and packaged in a single mode, a multi-channel tunable light source, a modulator array, a photoelectric detector PD array, a transimpedance amplifier array, an analog-to-digital conversion array, two digital-to-analog conversion arrays, a control circuit array and a memory array. The device for the optical pulse neural network processor is characterized in that an optical pulse neural network chip is based on III/V group monolithic integration, the output end of a multi-channel tunable light source is connected with the optical input end of a modulator array, the output end of the modulator array is respectively connected with the input end of the optical pulse neural network chip, the two output ends of a controller are connected with the input ends of two digital-to-analog conversion arrays, the output ends of the two digital-to-analog conversion arrays are respectively connected with the radio frequency end of the modulator and the current control end of the optical pulse neural network chip, the output end of the optical pulse neural network chip is connected with the input end of a PD array, the output end of the PD array is connected with the input end of a transimpedance amplifier array, the output end of the transimpedance amplifier array is connected with the input end of an analog-to-digital conversion array, the output end of the analog-to-digital conversion array is connected with the input end of a control circuit, and the control circuit is connected with a memory for storing and reading data. The optical pulse neural network chip is characterized in that the output end of a modulator is connected with the input end of an on-chip beam splitter, the output end of the beam splitter is connected with the input end of an array waveguide grating, the output end of the array waveguide grating is connected with the input end of an SOA synapse, the output end of the SOA synapse is connected with the input end of a second array waveguide grating, the output end of the second array waveguide grating i