Ranovus and AMD have demonstrated the CPO 2.0 solution for AI/ML platforms that demand power efficient, high throughput and high-density optical interconnect.

Ranovus’ Odin is a low latency, high density, and protocol agnostic optical engine that is capable of delivering massive optical interconnect bandwidth and power efficiency.  It is capable of scaling from 800Gbps to 3.2Tbps in the same footprint by leveraging Ranovus’ 100Gbps per lambda monolithic Electro-Photonic Integrated Circuit (EPIC) IP, laser platform, and advanced packaging technologies.

Announcing the Odin Analog Drive CPO 2.0 platform at OFC 2021 for Ethernet switch and module applications it was showcased with a Versal ACAP for ML/AI workloads.

Commenting Hamid Arabzadeh, Chairman and Chief Executive Officer of Ranovus said, “We have been at the forefront of the CPO movement since 2018 and are delighted to share our multi-disciplinary IP cores with our customers who want to accelerate the adoption of Analog Drive CPO in data centres.”  

CPO is an approach that provides Nx100Gbps PAM4 Optical I/O channels for Ethernet switch and ML/AI silicon in a single packaged assembly, significantly reducing the cost and power consumption of the complete system.

Versal is the industry’s first adaptive compute acceleration platform (ACAP) and by integrating the optics into the package using Versal Premium ACAPs, AMD and Ranovus have been able to drastically reduce power, simplify board routing, and reduce cost.

“We’re proud of our collaboration with Ranovus that helped achieve record performance levels while at the same time reducing power and overall footprint of the complete solution,” said Dan Mansur, vice president, Adaptable and Embedded Computing Group, AMD (formerly Xilinx). “This CPO demonstration highlights the versatility of the Versal GTM SERDES to operate over anything from long-reach copper to directly driving the Ranovus Analog-Drive CPO 2.0 optical engine. Co-packaging Ranovus Odin with Xilinx Versal is a significant advancement which enables data centre customers to build highly efficient and cost-effective systems for next-generation workloads.”