Silicon photonic subspace neural chip for hardware-efficient deep learning

Silicon photonic subspace neural chip for hardwareefficient deep learning Chenghao Feng, Jiaqi Gu, Hanqing Zhu, Zhoufeng Ying, Zheng Zhao, David Z. Pan , Ray T. Chen Microelectronics Research Center, The University of Texas at Austin, Austin, Texas 78758, USA. Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas 78705, USA. Alpine Optoelectronics, CA, USA. Synopsys Inc., CA, USA. Omega Optics, Inc., 8500 Shoal Creek Blvd., Bldg. 4, Suite 200, Austin, TX 78757, USA. These authors contributed equally. Corresponding authors: chenrt@austin.utexas.edu, dpan@ece.utexas.edu

[1]  M. Burla,et al.  Nano–opto-electro-mechanical switches operated at CMOS-level voltages , 2019, Science.

[2]  Song Han,et al.  EIE: Efficient Inference Engine on Compressed Deep Neural Network , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[3]  C. Wright,et al.  Photonics for artificial intelligence and neuromorphic computing , 2020, ArXiv.

[4]  David A. B. Miller,et al.  Parallel Programming of an Arbitrary Feedforward Photonic Network , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[5]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

[6]  Chao Wang,et al.  CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-Circulant Weight Matrices , 2017, 2017 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[7]  Andrea Fiore,et al.  Nano-opto-electro-mechanical systems , 2018, Nature Nanotechnology.

[8]  H. Zimmermann,et al.  Zero-bias 40Gbit/s germanium waveguide photodetector on silicon. , 2012, Optics express.

[9]  Yun Liang,et al.  Efficient Recurrent Neural Networks using Structured Matrices in FPGAs , 2018, ICLR.

[10]  Michael R. Watts,et al.  APSUNY Process Design Kit (PDKv3.0): O, C and L Band Silicon Photonics Component Libraries on 300mm Wafers , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[11]  Xu Wang,et al.  Chip-Scale Optical Matrix Computation for PageRank Algorithm , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[12]  Luca P. Carloni,et al.  Silicon Photonics Codesign for Deep Learning , 2020, Proceedings of the IEEE.

[13]  Ivan V. Oseledets,et al.  Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition , 2014, ICLR.

[14]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[15]  Paul R. Prucnal,et al.  Silicon Photonic Modulator Neuron , 2018, Physical Review Applied.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Philippe M. Bardet,et al.  Massively parallel amplitude-only Fourier neural network , 2020, Optica.

[18]  Xuan Li,et al.  Parallel convolutional processing using an integrated photonic tensor core , 2021, Nature.

[19]  K. Steinhubl.  Design of Ion-Implanted MOSFET'S with Very Small Physical Dimensions , 1974 .

[20]  Vivienne Sze,et al.  Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks , 2017, IEEE Journal of Solid-State Circuits.

[21]  Jiaming Zhang,et al.  Analogue signal and image processing with large memristor crossbars , 2017, Nature Electronics.

[22]  Huaxi Gu,et al.  Countering Variations and Thermal Effects for Accurate Optical Neural Networks , 2020, 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[23]  Bin Gao,et al.  Fully hardware-implemented memristor convolutional neural network , 2020, Nature.

[24]  Xu Han,et al.  Efficient training and design of photonic neural network through neuroevolution , 2019, Optics express.

[25]  Ray T. Chen,et al.  Wavelength-division-multiplexing (WDM)-based integrated electronic–photonic switching network (EPSN) for high-speed data processing and transportation , 2020 .

[26]  Zhenhua Ni,et al.  Monolayer graphene as a saturable absorber in a mode-locked laser , 2010, 1007.2243.

[27]  Ellen Zhou,et al.  Neuromorphic photonic networks using silicon photonic weight banks , 2017, Scientific Reports.

[28]  David A. Patterson,et al.  In-datacenter performance analysis of a tensor processing unit , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[29]  Shanhui Fan,et al.  Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks , 2019, IEEE Journal of Selected Topics in Quantum Electronics.

[30]  Xiao-ping Liu,et al.  High performance ultra-compact SOI waveguide crossing. , 2018, Optics express.

[31]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[32]  David A. B. Miller,et al.  Analyzing and generating multimode optical fields using self-configuring networks , 2020, Optica.

[33]  Shanhui Fan,et al.  Training of Photonic Neural Networks through In Situ Backpropagation , 2018, 2019 Conference on Lasers and Electro-Optics (CLEO).

[34]  Gabriela Nicolescu,et al.  Modeling fabrication non-uniformity in chip-scale silicon photonic interconnects , 2016, 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[35]  Ray T. Chen,et al.  Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization , 2020, AAAI.

[36]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[37]  Jiaqi Gu,et al.  Towards Area-Efficient Optical Neural Networks: An FFT-based Architecture , 2020, 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC).

[38]  Thomas Taubner,et al.  Phase-change materials for non-volatile photonic applications , 2017, Nature Photonics.

[39]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[40]  Ray T. Chen,et al.  Toward High‐Speed and Energy‐Efficient Computing: A WDM‐Based Scalable On‐Chip Silicon Integrated Optical Comparator , 2021, Laser & Photonics Reviews.

[41]  Rajeev J Ram,et al.  Integrating photonics with silicon nanoelectronics for the next generation of systems on a chip , 2018, Nature.

[42]  Jiaqi Gu,et al.  Electronic-photonic arithmetic logic unit for high-speed computing , 2020, Nature Communications.

[43]  Jiaqi Gu,et al.  ROQ: A Noise-Aware Quantization Scheme Towards Robust Optical Neural Networks with Low-bit Controls , 2020, 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[44]  Takuo Tanemura,et al.  Robust Integrated Optical Unitary Converter Using Multiport Directional Couplers , 2020, Journal of Lightwave Technology.

[45]  Xiaogang Wang,et al.  Convolutional neural networks with low-rank regularization , 2015, ICLR.

[46]  Hai Li,et al.  Group Scissor: Scaling neuromorphic computing design to large neural networks , 2017, 2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC).

[47]  Zhiru Zhang,et al.  Building Efficient Deep Neural Networks With Unitary Group Convolutions , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[49]  Krishnendu Chakrabarty,et al.  Modeling Silicon-Photonic Neural Networks under Uncertainties , 2020, 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[50]  S. Y. Siew,et al.  Review of Silicon Photonics Technology and Platform Development , 2021, Journal of Lightwave Technology.

[51]  Eriko Nurvitadhi,et al.  Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Neural Networks? , 2017, FPGA.

[52]  Dirk Englund,et al.  Deep learning with coherent nanophotonic circuits , 2017, 2017 Fifth Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S).

[53]  A. Boes,et al.  11 TOPS photonic convolutional accelerator for optical neural networks , 2021, Nature.

[54]  Mark Wade,et al.  TeraPHY: A Chiplet Technology for Low-Power, High-Bandwidth In-Package Optical I/O , 2020, IEEE Micro.

[55]  Jason Cong,et al.  Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks , 2015, FPGA.

[56]  E. Eleftheriou,et al.  Memory devices and applications for in-memory computing , 2020, Nature Nanotechnology.

[57]  Hong Cai,et al.  Efficient On-Chip Training of Optical Neural Networks Using Genetic Algorithm , 2021, ACS Photonics.

[58]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[59]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[60]  D. Dai,et al.  Ultra-Compact Broadband 2 × 2 3 dB Power Splitter Using a Subwavelength-Grating-Assisted Asymmetric Directional Coupler , 2020, Journal of Lightwave Technology.

[61]  Joel Emer,et al.  Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks , 2016, CARN.

[62]  A. Biberman,et al.  An ultralow power athermal silicon modulator , 2014, Nature Communications.

[63]  Jiaqi Gu,et al.  FLOPS: EFficient On-Chip Learning for OPtical Neural Networks Through Stochastic Zeroth-Order Optimization , 2020, 2020 57th ACM/IEEE Design Automation Conference (DAC).