Broadcom Inc. has unveiled expansions to its portfolio of optical interconnect solutions for artificial intelligence (AI) and machine learning applications.
The technologies will be used for the front-end and back-end networks at large-scale AI compute clusters, the company said.
The range includes:
- 200 Gbps per lane EML
- 200 G/lane VCSEL
- Continuous wave laser for silicon photonics
- More than 20 million channels of 100 G/lane optical components for AI/ML
Broadcom said that VCSEL and EML technologies are used in high-speed interconnects for AI and ML systems. Broadcom devices are currently used in AI networks to provide high bandwidth and interconnect density for interconnects. The new range will extend the speed and density.
The technologies allow for the use of existing capacity as end users progress to 1.6T optical transceivers and enter the era of terabit connectivity.
“Generative AI has unleashed a network transformation necessitating an order of magnitude increase in high-speed optical links compared to standard network requirements,” said Near Margalit, vice president and general manager of the Optical Systems Division at Broadcom. “We will continue to invest in VCSEL, EML and CW laser technologies to deliver disruptive innovation in bandwidth, power and latency for optical interconnects in next generation AI links.”
Broadcom will showcase these technologies at the Optical Fiber Communication 2024 trade show in San Diego, California, on March 26-28.
