Nvidia Feynman Pushes TSMC A16 and CPO Ramp
8 Articles
8 Articles
digitimes.com
technewstube.comNvidia Feynman pushes TSMC A16 and CPO ramp
Nvidia is accelerating development and supply-chain alignment for its Feynman generation in the second half of 2028, even as Vera Rubin enters mass production and ramps up. The move is set to drive upgrades at TSMC and could trigger another wave of orders across the global equipment and materials supply chain.
NVIDIA is still deploying Vera Rubin, but the company would already be mobilizing its supply chain to prepare for the next generational leap, and apparently it will be monstrous. We are talking about NVIDIA Feynman, a platform planned for the second half of 2028 that would combine the lithographic process of TSMC, specifically A16, 3D chiplet stacking, custom HBM memory and optical connections integrated through CPO.
NVIDIA Feynman GPU Rumored to Use TSMC A16, 3D Chiplets, Custom HBM and Co-Packaged Optics
NVIDIA's post-Rubin GPU architecture, Feynman, is reportedly being developed around TSMC's A16 manufacturing process, accompanied by significantly more aggressive 3D chip integration than today's Blackwell and upcoming Rubin products.
As the Blackwell GPUs continue their deployment and future generations Rubin and Rubin Ultra have not yet made their commercial debut, NVIDIA would already be working on their successor. According to several sources close to the TSMC supply chain, Jensen Huang's company has launched the prototyping of its next architecture called Feynman, [...] The NVIDIA article is already preparing the post-Rubin: Feynman architecture would adopt the TSMC A16 …
Nvidia may redesign Feynman AI platform due to manufacturing constraints
Nvidia's potential redesign of Feynman AI could delay innovation, impacting competitive edge and market dynamics in advanced computing. The post Nvidia may redesign Feynman AI platform due to manufacturing constraints appeared first on Crypto Briefing.
NVIDIA Secures TSMC A16 Node for Next-Generation "Feynman" GPUs
According to supply chain sources and those close to TSMC, NVIDIA is already working on prototyping the replacement for its "Rubin" and "Rubin Ultra" GPU designs with the next-generation "Feynman" GPU microarchitecture. As noted in the latest report from DigiTimes, NVIDIA is opting for TSMC's A16 node, bypassing the N2 family of nodes entirely in favor of the more advanced 1.6 nm A16 design. Mass production is scheduled for the second half of 20…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
