Read
AUTHORPÆDIA is hosted by Authorpædia Foundation, Inc. a U.S. non-profit organization.
Svetlana Velmar-Janković
| Launching | 2028 |
|---|---|
| Designed by | Nvidia |
| Manufactured by | |
| Specifications | |
| Memory support | HBM[1] |
| History | |
| Predecessor | Rubin |
Feynman is a microarchitecture for GPUs by Nvidia announced at Nvidia GTC in 2025 by CEO Jensen Huang. It is named after theoretical physicist Richard Feynman. It will use a Vera CPU from the preceding generation microarchitecture Vera Rubin and is planned to be released in 2028.[2][3][4] Feynman will use High Bandwidth Memory (HBM).[1] Nvidia is using its own Blackwell GPUs to accelerate the design of Feynman.[5]
See also
References
- ^ a b Hassan Mujtaba (March 18, 2025). "NVIDIA Unveils Next-Gen Feynman GPU In Updated Roadmap, Arriving in 2028 With Next-Gen HBM Memory". wccftech.
- ^ Benj Edwards (March 18, 2025). "Nvidia announces "Rubin Ultra" and "Feynman" AI chips for 2027 and 2028". Ars Technica.
- ^ Jeremy Laird (March 18, 2025). "While we despair of RTX 50-series supplies and wait on next-gen Rubin, Nvidia reveals its next-next GPU architecture will be known as Feynman and is due in 2028". PCGamer.
- ^ Kyle Wiggers (March 18, 2025). "Blackwell Ultra, Vera Rubin, and Feynman are Nvidia's next GPUs". Tech Crunch.
- ^ Nick Flaherty (March 18, 2025). "Nvidia accelerates Feynman chip design, manufacture on Blackwell GPU". eenews.