# Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects

arXiv: https://arxiv.org/abs/2504.15044 · HTML: https://mlsanity.com/paper/2504.15044/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 59 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [The physics of optical computing](https://mlsanity.com/paper/2308.00088/) (2023)
- [Deep Time-Delay Reservoir Computing: Dynamics and Memory Capacity](https://mlsanity.com/paper/2006.06322/) (2020)
- [Silicon photonic-electronic neural network for fibre nonlinearity compensation](https://mlsanity.com/paper/2110.12833/) (2021)
- [Microring resonators with external optical feedback for time delay reservoir computing](https://mlsanity.com/paper/2109.11486/) (2021)
- [Deep Photonic Reservoir Computer for Speech Recognition](https://mlsanity.com/paper/2312.06558/) (2023)
- [Photonic machine learning implementation for signal recovery in optical communications](https://mlsanity.com/paper/1710.01107/) (2017)
- [Deep photonic reservoir computing recurrent network](https://mlsanity.com/paper/2309.05246/) (2023)
- [PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing](https://mlsanity.com/paper/1807.05750/) (2018)
- [Experimental Investigation of a Recurrent Optical Spectrum Slicing Receiver for Intensity Modulation/Direct Detection systems using Programmable Photonics](https://mlsanity.com/paper/2406.16869/) (2024)

## Abstract (arXiv)

The rapid expansion of generative AI drives unprecedented demands for high-performance computing. Training large-scale AI models now requires vast interconnected GPU clusters across multiple data centers. Multi-scale AI training and inference demand uniform, ultra-low latency, and energy-efficient links to enable massive GPUs to function as a single cohesive unit. However, traditional electrical and optical interconnects, relying on conventional digital signal processors (DSPs) for signal distortion compensation, increasingly fail to meet these stringent requirements. To overcome these limitations, we present an integrated neuromorphic optical signal processor (OSP) that leverages deep reservoir computing and achieves DSP-free, all-optical, real-time processing. Experimentally, our OSP achieves a 100 Gbaud PAM4 per lane, 1.6 Tbit/s data center interconnect over a 5 km optical fiber in the C-band (equivalent to over 80 km in the O-band), far exceeding the reach of state-of-the-art DSP solutions, which are fundamentally constrained by chromatic dispersion in IMDD systems. Simultaneously, it reduces processing latency by four orders of magnitude and energy consumption by three orders of magnitude. Unlike DSPs, which introduce increased latency at high data rates, our OSP maintains consistent, ultra-low latency regardless of data rate scaling, making it ideal for future optical interconnects. Moreover, the OSP retains full optical field information for better impairment compensation and adapts to various modulation formats, data rates, and wavelengths. Fabricated using a mature silicon photonic process, the OSP can be monolithically integrated with silicon photonic transceivers, enhancing the compactness and reliability of all-optical interconnects. This research provides a highly scalable, energy-efficient, and high-speed solution, paving the way for next-generation AI infrastructure.