Chinese Researchers Develop Optical Chip Interconnect That Delivers 150× Faster AI Inference with One-Ninth the Computing Power

Peking University researchers develop new all-optical interconnect system linking standard electronic chips with specific algorithms

·         Researchers at Peking University have developed an all-optical interconnect system that links conventional electronic chips, significantly improving AI inference performance while drastically reducing computing requirements.

·         The new architecture achieved over 100-fold faster distributed AI inference while using only one-ninth of the computational resources typically required by a commercial GPU.

·         The research was published in the journal National Science Review.

·         The study was led by Shu Haowen and Wang Xingjun.

·         The system uses Field-Programmable Gate Arrays (FPGAs) as modular computing units, which are widely deployed in high-parallel processing applications such as autonomous driving, missile guidance and data centres.

·         The FPGA chips are interconnected using two custom optical communication components:

o    a 400 Gbps silicon photonic transceiver that converts electrical signals into optical signals and vice versa; and

o    a 16×16 optical switching chip that dynamically routes optical data between up to 16 input and 16 output ports.

·         Researchers connected five FPGA chips in parallel to perform an AI-based image-denoising task.

·         The system processed 1,000 images (32,768 bits each) in just 105.16 microseconds.

·         In comparison, a commercial 16.96-teraflop GPU completed the same task in 15.6 milliseconds, making the optical FPGA system nearly 150 times faster.

·         Despite the higher performance, the five FPGA chips together provided only 1.969 teraflops of theoretical computing power—less than one-ninth of the GPU's compute capability.

·         The performance advantage stems from the characteristics of optical communication, including:

o    optical switching losses below 5 decibels, enabling high-speed, error-free data transmission without external optical amplification; and

o    direct optical data flow between processing stages.

·         Unlike conventional GPU-based AI inference, where intermediate feature maps must repeatedly be written to and read from memory, the optical architecture allows data to flow directly between neural network layers, eliminating memory bottlenecks.

·         This pipeline-like processing keeps all processing units continuously active, reducing latency and improving overall hardware utilization.

·         The researchers conclude that future AI performance gains may depend more on intelligently connecting chips than simply increasing the number of processors.

·         The co-design of algorithms, processor architectures and chip-level optical interconnections could enable high-performance AI with significantly lower computational resources.

·         The technology also has the potential to reduce energy consumption in data centres and improve latency and power efficiency in edge-computing applications, making AI infrastructure more sustainable.

 

[ABS News Service/13.07.2026]

Chinese researchers have developed a new all-optical interconnect system linking standard electronic chips, boosting AI distributed inference speeds by over 100 times while using just one-ninth of the typical computational resources.

AI models are permeating ever more applications, expanding the industry’s appetite for computational power. The conventional response has been to pile on more GPUs and build ever-larger data centres in a seemingly endless race for energy and brute force.

But a new study from Peking University suggests a radically different path: by optically linking chips with specific algorithms, they boost inference speeds by a factor of over 100 while slashing compute needs to just one-ninth.

The work was published in the journal National Science Review, and its corresponding authors include Shu Haowen and Wang Xingjun from Peking University.

The team’s “Lego” building blocks were field-programmable gate array (FPGA) chips: programmable devices widely used in fields that demand high parallel-processing ability, such as missile guidance, autonomous driving and data centres.

The “joints” connecting these FPGAs are two custom-designed communication hardware components. The first is a silicon photonic transceiver chip running at 400 gigabits per second, responsible for converting electrical signals to optical and vice versa.

The second is a 16×16 optical switching chip that acts as a router during optical transmission and can establish arbitrary connections between up to 16 input ports and 16 output ports.

By wiring five FPGA chips in parallel, the researchers tackled an image-denoising task on a dedicated dataset, processing 1,000 images of 32,768 bits each in just 105.16 microseconds.

For comparison, the team ran the same image-denoising task on a commercial GPU rated at 16.96 teraflops. The GPU completed the task in 15.6 milliseconds, making the FPGA system nearly 150 times faster.

The five FPGAs together offered a combined theoretical compute power of about 1.969 teraflops – less than one-ninth the GPU’s resources.

This advantage stems from the inherent benefits of optical communication.

First, the switching chip’s total loss is below 5 decibels, enabling high-speed, error-free data transfer without any need for external optical gain compensation.

More importantly, in conventional GPU-based neural network inference, a cascade of intermediate results, namely feature maps, is generated between layers.

These must be stored and retrieved repeatedly, and each layer must wait for the previous one to finish before it can start, leaving compute units idle.

In optical computing, by contrast, results from one layer can flow directly into the next like an assembly line, bypassing memory altogether and keeping all chips continuously busy.

The research underscores a pivotal insight: in the relentless pursuit of AI compute power, “stacking more chips” might not be as effective as “connecting them intelligently”.

“Specific objectives can be realised under limited computational resources when algorithms, processor micro‑architectures and chip-level interconnections are co‑designed,” the authors wrote in the paper.

“This fabric can also alleviate unsustainable energy usage in data centres and optimise latency or consumption in edge-computing scenarios,” they added.