08LIGHT AS COMPUTE· SURGING

Optical Computing

Silicon photonics, co-packaged optics, photonic AI accelerators, optical neural networks

28SOURCES
7CONCEPTS
9ENTITIES
SOURCE MIX
15 P11 R2 A0 N
ACTIVITY · 20W
CPOPhotonicInterconnectSiPh
PAPER
2025-03-01

Integrated Platforms and Techniques for Photonic Neural Networks

npj Nanophotonics · npj Nanophotonics / Nature

Comprehensive review of integrated photonic platforms for neural networks

PAPER
2025-06-01

Integrated Neuromorphic Photonic Computing for AI Acceleration

Wang et al. · Advanced Materials / Wiley

Photonic tensor cores: 880 TOPS/mm2, 5.1 TOPS/W — 1-3 OOM over digital accelerators

PAPER
2026-03-09

Ultra-compact photonic AI chip operates at the speed of light

Joel Sved et al. · University of Sydney

Inverse-designed nanophotonic neural network achieving 90-99% classification accuracy on 10K+ biomedical images at picosecond timescales

PAPER
2025-06-01

An integrated large-scale photonic accelerator with ultralow latency

Nature · Various

16,000+ component photonic accelerator on single chip demonstrating ultralow latency and faster computing than commercial GPU

PAPER
2026-04-12

Harnessing Photonics for Machine Intelligence

Hanqing Zhu, Shupeng Ning, Hongjian Zhou, Ziang Yin, Ray T. Chen, Jiaqi Gu, David Z. Pan · University of Texas at Austin; Arizona State University

System-level cross-layer benchmarking framework (SimPhony) revealing that peripheral overheads dominate photonic AI energy budgets, and that dynamic Transformer workloads expose fundamental limitations in MZI mesh architectures

PAPER
2025-09-01

Integrated photonic neuromorphic computing: device, architecture, chip, algorithm

Shuiying Xiang, Chengyang Yu, Yizhi Wang, Xintao Zeng, Yuna Zhang, Dianzhuang Zheng, Xinran Niu, Haowen Zhao, Hanxu Zhou, Yanan Han, Xingxing Guo, Yahui Zhang, Yue Hao · Not specified (HTML unavailable at ingestion)

Systematic multi-layer review of photonic neuromorphic computing spanning photonic neurons, synapses, network architectures, integrated chips, and optimization algorithms

PAPER
2025-08-19

A fully-programmable integrated photonic processor for domain-specific and general-purpose computing

Feng-Kai Han, Xiao-Yun Xu, Tian-Yu Zhang, Lei Feng, Chu-Han Wang, Jie Ma, Ze-Feng Lan, Chao-Qian Li, Yi Xie, Hai Yan, Yu-Fei Liu, Yu-Quan Peng, Xian-Min Jin · Shanghai Jiao Tong University; Hefei National Laboratory; TuringQ Co., Ltd.

First single programmable photonic processor handling both NP-complete problem solving (100% accuracy) and general-purpose matrix computation (97% MNIST accuracy) without hardware modification

PAPER
2025-06-04

Quantum photonics on a chip

A. Katiyi, A. Karabchevsky · Ben-Gurion University of the Negev; Lancaster University

Comprehensive review of integrated quantum photonic circuits on chip, synthesizing materials platforms, single-photon sources, detectors, and applications across quantum computing, communication, and sensing

PAPER
2026-04-02

Photonic convolutional neural network with pre-trained in-situ training

Saurabh Ranjan, Sonika Thakral, Amit Sehgal

Fully-optical CNN for MNIST at 94% accuracy with 100-242x better energy efficiency than GPUs, 2132 on-chip tunable parameters, no O/E/O conversions.

PAPER
2026-03-01

Integrated photonic neural network with on-chip backpropagation training

Farshid Ashtiani, Mohamad Hossein Idjadi, Kwangwoong Kim · Nokia Bell Labs

First integrated photonic deep NN trained end-to-end with on-chip gradient-descent backpropagation — all linear AND nonlinear computation on a single photonic chip, robust to fabrication variations (>90% accuracy). Nature 651, 927-932 (2026). Answers the KB's 'training, not just inference' open question.

PAPER
2026-03-01

Inverse-designed nanophotonic neural network accelerators for ultra-compact optical computing

Joel Sved et al. · University of Sydney

Peer-reviewed Nature Communications paper for the Univ. of Sydney inverse-designed nanophotonic NN accelerator: ~400M parameters/mm2 via subwavelength voxels as trainable DOF; ~89% MNIST / ~90% MedNIST on-chip (90-99% on 10K+ biomedical images), picosecond/speed-of-light, human-hair footprint. Authority upgrade over the prior news-only entry.

PAPER
2026-04-09

Deep neural network inference on an integrated, reconfigurable photonic tensor processor

Lennart Meyer, Jelle Dijkstra, Simon Tebeck, Frank Brückerhoff-Plückelmann, Wolfram Pernice, et al. · University of Heidelberg; Volkswagen AG; Enlightra

imec iSiPP50G photonic tensor processor with PyTorch interface; honestly reports 0.022 TOPS/W vs 5.65 TOPS/W electronic — peripherals (DAC/ADC/TIA) dominate the energy budget, not the photonic core

PAPER
2026-02-26

SKYLIGHT: A Scalable Hundred-Channel 3D Photonic In-Memory Tensor Core for Real-Time AI Inference

SKYLIGHT authors · Multi-institution

SKYLIGHT proposes scalable 3D, WDM-enabled, non-volatile photonic tensor core architecture with hundred-channel parallelism for real-time AI inference

PAPER
2026-04-01

LightIn: Versatile Silicon Integrated Photonic Processor for AI Clusters

LightIn research team · Multi-institution

LightIn 160-component silicon photonic processor — first to realize compute + signal processing + switching + encryption on a single CMOS-compatible chip for AI clusters

PAPER
2026-04-01

Towards Topology-Aware Very Large-Scale Photonic AI Accelerators

(arXiv preprint authors — see paper) · Unspecified (arXiv preprint)

Identifies the 'Utilization Wall' — topology-dominated scaling bottleneck in photonic accelerators; symmetric-grid topologies recover up to 6x utilization, cut memory access >40%

REPORT
2026-03-11

Lightmatter Passage L200: Record 1.6 Tbps Per Fiber

Lightmatter · Lightmatter

Record 1.6 Tbps/fiber; L200 CPO enabling 200+ Tbps/package; 8x faster AI training

REPORT
1970-01-01

Ayar Labs UCIe Optical Chiplet

Ayar Labs · Ayar Labs

First UCIe optical chiplet. 16-wavelength SuperNova, 8 Tbps. TSMC COUPE partnership. $500M raise Mar 2026 (Nvidia-backed). Production samples 2026.

REPORT
2026-03-03

Ayar Labs raises $500M to mass-produce CPO chiplets

The Register · Ayar Labs

$500M Series E for CPO mass production; TeraPHY delivers 200 Tbps/package — 5x Nvidia Rubin bandwidth

REPORT
2025-10-01

TSMC COUPE Platform for Silicon Photonics — Alchip + Ayar Labs Demo

Tom's Hardware · TSMC, Alchip, Ayar Labs

First fully integrated COUPE-based optical I/O engine — 100 Tb/s per accelerator via UCIe interface

REPORT
2023-04-05

OIF 3.2T Co-Packaged Module Implementation Agreement

Optical Internetworking Forum · OIF

First industry co-packaging standard — 3.2Tb/s module with 8x400G optical interfaces enabling 51.2Tb/s switch bandwidth

REPORT
2025-11-19

Q.ANT NPU 2 Photonic Processor for AI and HPC

The Quantum Insider · Q.ANT

Second-gen photonic processor claiming 30x lower energy and 50x higher performance for AI/HPC, shipping early 2026

REPORT
2025-03-31

Lightmatter Unveils Passage M1000 Photonic Superchip, World's Fastest AI Interconnect

Lightmatter · Lightmatter

Passage M1000 3D photonic superchip — 114 Tbps total optical bandwidth, 256 fibers (448 Gbps/fiber), >4,000 mm2 8-tile 3D active photonic interposer with world-first built-in solid-state optical circuit switching; GF Fotonix + Amkor.

REPORT
2026-01-26

Lightmatter and GUC Partner to Produce Co-Packaged Optics (CPO) Solutions for AI Hyperscalers

Lightmatter · Lightmatter; Global Unichip Corp (GUC)

Lightmatter + GUC strategic partnership to bring commercial Passage 3D CPO to AI hyperscalers — pairs Lightmatter's 3D-stacked silicon photonics engine with GUC's advanced ASIC design + packaging to extend AI cluster scale-up across multiple racks.

REPORT
2025-03-18

NVIDIA Announces Spectrum-X Photonics, Co-Packaged Optics Networking Switches to Scale AI Factories to Millions of GPUs

NVIDIA Corporation · NVIDIA

NVIDIA's own CPO switch line — Spectrum-X Photonics (Ethernet, 2H 2026) + Quantum-X Photonics (InfiniBand, 2025); 3.5x power efficiency, 4x fewer lasers, up to 400Tb/s; closes the KB's top-flagged gap

REPORT
2025-10-17

Broadcom Announces Tomahawk 6 – Davisson, the Industry's First 102.4-Tbps Ethernet Switch with Co-Packaged Optics

Broadcom Inc. · Broadcom Inc.

3rd-gen CPO switch BCM78919: 102.4Tbps via 64x1.6TbE, 16 Davisson DR optical engines on TSMC COUPE, ~70% lower power, field-replaceable lasers; shipping since Oct 2025

REPORT
2026-05-11

Lightwave Logic Q1 2026 Earnings Call — Strategic Investment Focus

Lightwave Logic, Inc. · Lightwave Logic Inc. (NASDAQ: LWLG)

Q1 2026 revenue $29K (+27% YoY); PDK 1.1 handoff to production May 2026; 4 Fortune 500/Global 500 customers at Stage 3; ~$100M cash; FY26/27 guidance only $0.41M/$0.64M

ANALYSIS
1970-01-01

The Shift to Photonics for Data Center Networks and AI

Industry deployment timeline 2026-2028. Manufacturing, supply chain, integration realities.

ANALYSIS
2026-02-05

Five Key Trends of Co-Packaged Optics (CPO) in 2026

Siemens EDA · Siemens

Industry analysis: CPO reduces link power 30W→9W, UCIe optical extends package boundaries, thermal management is critical blocker

Optical Computing | Knowledge Base | MenFem