Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip

Optical neural networks (ONN) have become the most promising solution to replacing electronic neural networks, which have the advantages of large bandwidth, low energy consumption, strong parallel processing ability, and super high speed. Silicon-based micro-nano integrated photonic platforms have d...

Full description

Bibliographic Details
Main Authors: Xu Liu, Xudong Zhu, Chunqing Wang, Yifan Cao, Baihang Wang, Hanwen Ou, Yizheng Wu, Qixun Mei, Jialong Zhang, Zhe Cong, Rentao Liu
Format: Article
Language:English
Published: MDPI AG 2022-06-01
Series:Nanomaterials
Subjects:
Online Access:https://www.mdpi.com/2079-4991/12/13/2136
_version_ 1797442484652998656
author Xu Liu
Xudong Zhu
Chunqing Wang
Yifan Cao
Baihang Wang
Hanwen Ou
Yizheng Wu
Qixun Mei
Jialong Zhang
Zhe Cong
Rentao Liu
author_facet Xu Liu
Xudong Zhu
Chunqing Wang
Yifan Cao
Baihang Wang
Hanwen Ou
Yizheng Wu
Qixun Mei
Jialong Zhang
Zhe Cong
Rentao Liu
author_sort Xu Liu
collection DOAJ
description Optical neural networks (ONN) have become the most promising solution to replacing electronic neural networks, which have the advantages of large bandwidth, low energy consumption, strong parallel processing ability, and super high speed. Silicon-based micro-nano integrated photonic platforms have demonstrated good compatibility with complementary metal oxide semiconductor (CMOS) processing. Therefore, without completely changing the existing silicon-based fabrication technology, optoelectronic hybrid devices or all-optical devices of better performance can be achieved on such platforms. To meet the requirements of smaller size and higher integration for silicon photonic computing, the topology of a four-channel coarse wavelength division multiplexer (CWDM) and an optical scattering unit (OSU) are inversely designed and optimized by Lumerical software. Due to the random optical power splitting ratio and incoherency, the intensities of different input signals from CWDM can be weighted and summed directly by the subsequent OSU to accomplish arbitrary multiply–accumulate (MAC) operations, therefore supplying the core foundation for scattering ONN architecture.
first_indexed 2024-03-09T12:42:32Z
format Article
id doaj.art-18ec9cea42614d5daddfa4c4cbef7ca4
institution Directory Open Access Journal
issn 2079-4991
language English
last_indexed 2024-03-09T12:42:32Z
publishDate 2022-06-01
publisher MDPI AG
record_format Article
series Nanomaterials
spelling doaj.art-18ec9cea42614d5daddfa4c4cbef7ca42023-11-30T22:15:52ZengMDPI AGNanomaterials2079-49912022-06-011213213610.3390/nano12132136Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation ChipXu Liu0Xudong Zhu1Chunqing Wang2Yifan Cao3Baihang Wang4Hanwen Ou5Yizheng Wu6Qixun Mei7Jialong Zhang8Zhe Cong9Rentao Liu10National Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaNational Research Center for Optical Sensing/Communications Integrated Networking, Department of Electronics Engineering, Southeast University, Nanjing 210096, ChinaOptical neural networks (ONN) have become the most promising solution to replacing electronic neural networks, which have the advantages of large bandwidth, low energy consumption, strong parallel processing ability, and super high speed. Silicon-based micro-nano integrated photonic platforms have demonstrated good compatibility with complementary metal oxide semiconductor (CMOS) processing. Therefore, without completely changing the existing silicon-based fabrication technology, optoelectronic hybrid devices or all-optical devices of better performance can be achieved on such platforms. To meet the requirements of smaller size and higher integration for silicon photonic computing, the topology of a four-channel coarse wavelength division multiplexer (CWDM) and an optical scattering unit (OSU) are inversely designed and optimized by Lumerical software. Due to the random optical power splitting ratio and incoherency, the intensities of different input signals from CWDM can be weighted and summed directly by the subsequent OSU to accomplish arbitrary multiply–accumulate (MAC) operations, therefore supplying the core foundation for scattering ONN architecture.https://www.mdpi.com/2079-4991/12/13/2136optical neural network (ONN)multiply–accumulate (MAC) operationinverse designsilicon-on-insulator (SOI)metastructurecoarse wavelength division multiplexer (CWDM)
spellingShingle Xu Liu
Xudong Zhu
Chunqing Wang
Yifan Cao
Baihang Wang
Hanwen Ou
Yizheng Wu
Qixun Mei
Jialong Zhang
Zhe Cong
Rentao Liu
Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
Nanomaterials
optical neural network (ONN)
multiply–accumulate (MAC) operation
inverse design
silicon-on-insulator (SOI)
metastructure
coarse wavelength division multiplexer (CWDM)
title Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
title_full Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
title_fullStr Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
title_full_unstemmed Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
title_short Silicon-Based Metastructure Optical Scattering Multiply–Accumulate Computation Chip
title_sort silicon based metastructure optical scattering multiply accumulate computation chip
topic optical neural network (ONN)
multiply–accumulate (MAC) operation
inverse design
silicon-on-insulator (SOI)
metastructure
coarse wavelength division multiplexer (CWDM)
url https://www.mdpi.com/2079-4991/12/13/2136
work_keys_str_mv AT xuliu siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT xudongzhu siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT chunqingwang siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT yifancao siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT baihangwang siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT hanwenou siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT yizhengwu siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT qixunmei siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT jialongzhang siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT zhecong siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip
AT rentaoliu siliconbasedmetastructureopticalscatteringmultiplyaccumulatecomputationchip