Feynman Architecture Opens the Era of Chip Optical Interconnection; CPO Industry Faces Revaluation

Chip-to-chip interconnect, as the core of the world’s AI compute infrastructure, is now undergoing a historic transition from “electricity” to “light.” On March 16 local time, NVIDIA released the Feynman chip, for the first time bringing optical communication into chip-to-chip interconnects, which can reduce AI data center communication energy consumption by more than 70%. Analysts believe that, as overseas technology pathways are established and domestic industrial policies are further strengthened, optical module leaders listed on the A-share market that are deeply embedded in the global compute supply chain, as well as manufacturers with CPO technology reserves, are likely to be the first to enter the period of earnings realization amid the new infrastructure wave of “compute and power coordination.” (China Securities Journal)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments