{"title":"面向机器学习应用的电子-光子集成电路硬件加速器的分析与代码设计","authors":"A. Mosses, P. M. Joe Prathap","doi":"10.1007/s10825-023-02123-8","DOIUrl":null,"url":null,"abstract":"<p>Innovations in deep learning technology have recently focused on photonics as a computing medium. Integrating an electronic and photonic approach is the main focus of this work utilizing various photonic architectures for machine learning applications. The speed, power, and reduced footprint of these photonic hardware accelerators (HA) are expected to greatly enhance inference. In this work, we propose a hybrid design of an electronic and photonic integrated circuit (EPIC) hardware accelerator (EPICHA), an electronic–photonic framework that uses architecture-level integrations for better performance. The proposed EPICHA has a systematic structure of reconfigurable directional couplers (RDCs) to build a scalable, efficient machine learning accelerator for inference applications. In the simulation framework, the input and output layers of a fully integrated photonic neural network use the same integrated photodetector and RDC technology as the activation function. Our system only compromises on latency because of the electro–optical conversion process and the hand-off between the electronic and photonic domains. Insertion losses in photonic components have a small negative impact on accuracy when using more deep learning stages. Our proposed EPICHA utilizes coherent operation, and hence uses a single wavelength of <i>λ</i> = 1550 nm. We used the interoperability feature of the Ansys Lumerical MODE, DEVICE, and INTERCONNECT tools for component modeling in the photonic and electrical domain, and circuit-level simulation using <i>S</i>-parameters with MATLAB. The electronic component acts as the controller, which generates the required analog voltage control signals for each RDC present in the photonic processing engine. We employed MathWorks MATLAB 2022b for the classification of handwritten digits from the MNIST database; the proposed coherent EPICHA achieved accuracy of 94%.</p>","PeriodicalId":620,"journal":{"name":"Journal of Computational Electronics","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis and codesign of electronic–photonic integrated circuit hardware accelerator for machine learning application\",\"authors\":\"A. Mosses, P. M. Joe Prathap\",\"doi\":\"10.1007/s10825-023-02123-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Innovations in deep learning technology have recently focused on photonics as a computing medium. Integrating an electronic and photonic approach is the main focus of this work utilizing various photonic architectures for machine learning applications. The speed, power, and reduced footprint of these photonic hardware accelerators (HA) are expected to greatly enhance inference. In this work, we propose a hybrid design of an electronic and photonic integrated circuit (EPIC) hardware accelerator (EPICHA), an electronic–photonic framework that uses architecture-level integrations for better performance. The proposed EPICHA has a systematic structure of reconfigurable directional couplers (RDCs) to build a scalable, efficient machine learning accelerator for inference applications. In the simulation framework, the input and output layers of a fully integrated photonic neural network use the same integrated photodetector and RDC technology as the activation function. Our system only compromises on latency because of the electro–optical conversion process and the hand-off between the electronic and photonic domains. Insertion losses in photonic components have a small negative impact on accuracy when using more deep learning stages. Our proposed EPICHA utilizes coherent operation, and hence uses a single wavelength of <i>λ</i> = 1550 nm. We used the interoperability feature of the Ansys Lumerical MODE, DEVICE, and INTERCONNECT tools for component modeling in the photonic and electrical domain, and circuit-level simulation using <i>S</i>-parameters with MATLAB. The electronic component acts as the controller, which generates the required analog voltage control signals for each RDC present in the photonic processing engine. We employed MathWorks MATLAB 2022b for the classification of handwritten digits from the MNIST database; the proposed coherent EPICHA achieved accuracy of 94%.</p>\",\"PeriodicalId\":620,\"journal\":{\"name\":\"Journal of Computational Electronics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-01-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Computational Electronics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s10825-023-02123-8\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computational Electronics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10825-023-02123-8","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Analysis and codesign of electronic–photonic integrated circuit hardware accelerator for machine learning application
Innovations in deep learning technology have recently focused on photonics as a computing medium. Integrating an electronic and photonic approach is the main focus of this work utilizing various photonic architectures for machine learning applications. The speed, power, and reduced footprint of these photonic hardware accelerators (HA) are expected to greatly enhance inference. In this work, we propose a hybrid design of an electronic and photonic integrated circuit (EPIC) hardware accelerator (EPICHA), an electronic–photonic framework that uses architecture-level integrations for better performance. The proposed EPICHA has a systematic structure of reconfigurable directional couplers (RDCs) to build a scalable, efficient machine learning accelerator for inference applications. In the simulation framework, the input and output layers of a fully integrated photonic neural network use the same integrated photodetector and RDC technology as the activation function. Our system only compromises on latency because of the electro–optical conversion process and the hand-off between the electronic and photonic domains. Insertion losses in photonic components have a small negative impact on accuracy when using more deep learning stages. Our proposed EPICHA utilizes coherent operation, and hence uses a single wavelength of λ = 1550 nm. We used the interoperability feature of the Ansys Lumerical MODE, DEVICE, and INTERCONNECT tools for component modeling in the photonic and electrical domain, and circuit-level simulation using S-parameters with MATLAB. The electronic component acts as the controller, which generates the required analog voltage control signals for each RDC present in the photonic processing engine. We employed MathWorks MATLAB 2022b for the classification of handwritten digits from the MNIST database; the proposed coherent EPICHA achieved accuracy of 94%.
期刊介绍:
he Journal of Computational Electronics brings together research on all aspects of modeling and simulation of modern electronics. This includes optical, electronic, mechanical, and quantum mechanical aspects, as well as research on the underlying mathematical algorithms and computational details. The related areas of energy conversion/storage and of molecular and biological systems, in which the thrust is on the charge transport, electronic, mechanical, and optical properties, are also covered.
In particular, we encourage manuscripts dealing with device simulation; with optical and optoelectronic systems and photonics; with energy storage (e.g. batteries, fuel cells) and harvesting (e.g. photovoltaic), with simulation of circuits, VLSI layout, logic and architecture (based on, for example, CMOS devices, quantum-cellular automata, QBITs, or single-electron transistors); with electromagnetic simulations (such as microwave electronics and components); or with molecular and biological systems. However, in all these cases, the submitted manuscripts should explicitly address the electronic properties of the relevant systems, materials, or devices and/or present novel contributions to the physical models, computational strategies, or numerical algorithms.