Source – AMD
AI models are growing larger and more complex in nature. Its need for faster, more efficient data movement is also accelerating. To meet these evolving demands, particularly at the rack scale, optical interconnects offer a compelling path forward. Brian Amick, Senior Vice President- Technology and Engineering at AMD writes in a blog that ‘Co-packaged optics‘ can deliver higher bandwidth density and better power efficiency than traditional approaches, representing a transformative step in system architecture where tighter integration between compute and networking is enabled to support the performance and scale that advanced AI workloads require.
Marking a significant advancement in the company’s rapidly evolving AI strategy, AMD has officially acquired Enosemi.
Enosemi previously collaborated with AMD as an external development partner focused on photonics. This acquisition strengthens that relationship, enabling AMD to immediately scale its capabilities in developing a wide range of photonics and co-packaged optics solutions for next-generation AI systems.
The Enosemi team, based in Silicon Valley, comprises elite experts and PhD-holding talent with a strong track record in designing and delivering photonic integrated circuits at scale, a rare achievement accomplished by only a select few in the industry. Their deep technical expertise, executional excellence, and innovation in high-performance interconnects make them a strategic fit for AMD’s continued growth in advanced AI infrastructure.
AMD has been building a best-in-class portfolio to address the rapidly evolving needs of AI, from foundational silicon to systems-level integration. That journey has included integrating Xilinx’s industry-leading AI Engines and adaptive SoC technologies, adding advanced data movement and networking capabilities through Pensando, building a world-class software team with the additions of Silo AI and Mipsology, and scaling full rack-level system design with the acquisition of ZT Systems.
Looking ahead, the demands of AI systems will require not just powerful chips, but full-stack innovation across compute, networking, systems architecture, software and more. AMD is uniquely positioned to deliver across this stack, bringing together industry-leading CPUs, GPUs, and adaptive SoCs with deep networking, software, and system integration expertise.
