Integrated Photonic Tensor Processing Unit for a Matrix Multiply: a Review

Abstract

The explosion of artificial intelligence and machine-learning algorithms, connected to the exponential growth of the exchanged data, is driving a search for novel application-specific hardware accelerators. Among the many, the photonics field appears to be in the perfect spotlight for this global data explosion, thanks to its almost infinite bandwidth capacity associated with limited energy consumption. In this review, we will overview the major advantages that photonics has over electronics for hardware accelerators, followed by a comparison between the major architectures implemented on Photonics Integrated Circuits (PIC) for both the linear and nonlinear parts of Neural Networks. By the end, we will highlight the main driving forces for the next generation of photonic accelerators, as well as the main limits that must be overcome.

References in corpus (32)

• Deep Learning in Neural Networks: An Overview
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Deep Learning with Coherent Nanophotonic Circuits
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Parallel convolution processing using an integrated photonic tensor core
• Photonics for artificial intelligence and neuromorphic computing
• Universal Linear Optics
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Neuromorphic Silicon Photonic Networks
• Single-chip photonic deep neural network for instantaneous image classification
• Attojoule Optoelectronics for Low-Energy Information Processing and Communications: a Tutorial Review
• Self-Configuring Universal Linear Optical Component
• A silicon photonic modulator neuron
• Hybrid integration of silicon photonics circuits and InP lasers by photonic wire bonding
• All-optical mode unscrambling on a silicon photonic chip
• Photonic tensor cores for machine learning
• Prospects and applications of photonic neural networks
• CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
• Survey and Benchmarking of Machine Learning Accelerators
• Silicon microring synapses enable photonic deep learning beyond 9-bit precision
• Survey of Machine Learning Accelerators
• Resiliency of Deep Neural Networks under Quantization
• Scaling Up Silicon Photonic-based Accelerators: Challenges and Opportunities
• Waveguide based Electroabsorption Modulator Performance
• Noise Analysis of Photonic Modulator Neurons
• An ITO Graphene hybrid integrated absorption modulator on Si-photonics for neuromorphic nonlinear activation
• Quantifying power use in silicon photonic neural networks
• MorphoNoC: Exploring the Design Space of a Configurable Hybrid NoC using Nanophotonics
• Electronic Bottleneck Suppression in Next-generation Networks with Integrated Photonic Digital-to-analog Converters
• Highly Accurate, Reliable and Non-Contaminating Two-Dimensional Material Transfer System
• 45-year CPU evolution: one law and two equations
• Reconfigurable Application-Specific Photonic Integrated Circuit for solving Partial Differential Equations

Cited by in corpus (3)

• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Symmetric silicon microring resonator optical crossbar array for accelerated inference and training in deep learning
• Braided interferometer mesh for robust photonic matrix-vector multiplications with non-ideal components