NVIDIA's Next-Gen Graphics Card to Debut with 1.6nm Process A16, Limited Capacity Forces Hybrid 3nm Integration

13 hour ago / Read about 0 minute

Author：小编

At last week's GTC 2026 conference, NVIDIA unveiled the roadmap for its next-generation AI data center platform, centered around the GPU architecture codenamed Feynman, expected to officially launch in 2028. This architecture will adopt TSMC's 1.6nm A16 manufacturing process and introduce 3D Die Stacking packaging technology for the first time, enhancing performance through vertical stacking of GPU logic units. Meanwhile, Feynman will feature customized HBM memory, further optimizing storage bandwidth. Additionally, NVIDIA announced a foundry partnership with Intel to leverage its EMIB advanced packaging technology for Feynman chip production.

Previous page：Memory Production Capacity Sees Massive Boost: SK ...

Next page：Qinghe Jingyuan Raises Around 500 Million Yuan in ...

Return to List

Hot Reading

2 day ago

Cursor admits its new coding model was built on top of Moonshot AI’s Kimi

2 day ago

An exclusive tour of Amazon’s Trainium lab, the chip that’s won over Anthropic, OpenAI, even Apple

2 day ago

Are AI tokens the new signing bonus or just a cost of doing business?

2 day ago

The SEC drops its four-year-old investigation into EV startup Faraday Future