Quantization-aware Photonic Homodyne computing for Accelerated Artificial Intelligence and Scientific Simulation

2026-02-09

AI Summary

This work addresses the limitations of photonic analog computing—namely electro-optic distortion, material nonlinearity, and low signal-to-noise ratio—which hinder its application in high-precision AI and scientific computing. The authors propose the first quantization-aware digital–photonic mixed-precision framework, leveraging in-phase optical logic to enable high-speed complex matrix multiplication. By co-designing quantization algorithms with photonic hardware and integrating amplitude–phase decoupling with an inter-chip mixed-precision architecture, the system achieves digital-level accuracy while retaining the high bandwidth and energy efficiency of photonics. Implemented on a lithium niobate platform with channel equalization, iterative solvers, and bit-sliced sparse-dense quantization, the system delivers 6-bit precision linear multiplication at 128 GS/s (6 ns AI inference latency) and attains 12-bit precision in solving electromagnetic scattering partial differential equations, matching the accuracy of conventional 32/64-bit digital methods.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Modern problems in high-performance computing, ranging from training and inferencing deep learning models in computer vision and language models to simulating complex physical systems with nonlinearly-coupled equations, require exponential growth of computational resources. Photonic analog systems are emerging with solutions of intrinsic parallelism, high bandwidth, and low propagation loss. However, their application has been hindered by the low analog accuracy due to the electro-optic distortion, material nonlinearities, and signal-to-noise ratios. Here we overcome this barrier with a quantization-aware digital-photonic mixed-precision framework across chiplets for accelerated AI processing and physical simulation. Using Lithium Niobate photonics with channel equalization techniques, we demonstrate linear multiplication (9-bit amplitude-phase decoupling) in homodyne optical logics with 6-bit precision at the clock rate of 128 giga-symbol-per-second (128 GS/s), enabling AI processing with 6 ns latency. Codesign hardware-algorithms, including iterative solvers, sparse-dense quantization, and bit-sliced matrix multiplication, explore photonic amplitude and phase coherence for complex-valued, physics-inspired computation. In electromagnetic problems, our approach yields 12-bit solutions for partial differential equations (PDEs) in scattering problems that would conventionally require up to 32-bit and often even 64-bit precision. These results preserve digital-level fidelity while leveraging the high-speed low-energy photonic hardware, establishing a pathway toward general-purpose optical acceleration for generative artificial intelligence, real-time robotics, and accurate simulation for climate challenges and biological discoveries.

Problem

• photonic computing
• analog accuracy
• quantization
• optical acceleration
• computational precision

Innovation

• Quantization-aware computing
• Photonic homodyne computing
• Mixed-precision framework
• Lithium Niobate photonics
• Amplitude-phase decoupling