Lightmatter Integrates Synopsys IP for High-Performance 3D Photonic AI Engines

Lightmatter is partnering with Synopsys to integrate advanced interface technology into its groundbreaking 3D photonic AI engines, promising a significant leap forward for hyperscale AI infrastructure. Announced January 26, 2026, the collaboration will see Synopsys’ 224G SerDes and UCIe IP for the 3nm process incorporated into Lightmatter’s Passage™ platform. This co-packaged optics solution aims to maximize power efficiency, reliability, and bandwidth for next-generation AI. “As AI models grow in size and complexity, the efficiency of the electrical interface to the optical engine becomes a critical design factor,” said Ritesh Jain, SVP of Engineering & Operations at Lightmatter. By streamlining the electrical-to-optical connection, Lightmatter and Synopsys are tackling a key bottleneck in scaling AI clusters beyond current limitations.

Synopsys 224G SerDes & UCIe IP Integrate with Passage CPO

The integration of Synopsys’ 224G SerDes and UCIe IP with Lightmatter’s Passage Co-Packaged Optics (CPO) platform marks a significant step towards scaling next-generation AI infrastructure, specifically targeting hyperscale deployments. This collaboration centers on optimizing the crucial electrical-to-optical interface, ensuring seamless high-bandwidth connectivity between AI accelerators and Lightmatter’s 3D photonic engine built on a 3nm process. Synopsys will contribute tools like 3DIC Compiler and the Lumerical product suite to accelerate co-design of electrical and photonic components. Neeraj Paliwal, senior vice president of IP product management at Synopsys, states, “By integrating our silicon-proven 224G SerDes and UCIe IP into Lightmatter’s Passage 3D Co-Packaged Optics platform, we’re delivering a high-bandwidth, low-latency, and energy-efficient solution ready for scale up and out connectivity.” Alan Weckel of 650 Group highlights this as a “vital step in the maturation of the CPO ecosystem.”

The resulting platform is designed to enhance bandwidth and energy efficiency, leveraging the inherent benefits of Lightmatter’s 3D architecture alongside optimized SerDes and UCIe IP.

Dr. Donovan

Dr. Donovan

Dr. Donovan is a futurist and technology writer covering the quantum revolution. Where classical computers manipulate bits that are either on or off, quantum machines exploit superposition and entanglement to process information in ways that classical physics cannot. Dr. Donovan tracks the full quantum landscape: fault-tolerant computing, photonic and superconducting architectures, post-quantum cryptography, and the geopolitical race between nations and corporations to achieve quantum advantage. The decisions being made now, in research labs and government offices around the world, will determine who controls the most powerful computers ever built.

Latest Posts by Dr. Donovan:

The mind and consciousness explored through cognitive science

Two Clicks Enough for Expert Echolocators to Sense Objects

April 8, 2026
Bloomberg: 21 Factored: Quantum Risk to Crypto Not Imminent Now

Adam Back Says Quantum Risk to Crypto Not Imminent Now

April 8, 2026
Fully programmable quantum computing with trapped-ions

Fully programmable quantum computing with trapped-ions

April 8, 2026