❌

Normal view

There are new articles available, click to refresh the page.
Before yesterdayMain stream

NVIDIA’s Rubin Ultra Reportedly Scaled Back to Dual-Die Design, Instead of the Ambitious Four-Die One, Amid Supply Chain Concerns

1 April 2026 at 13:56

A circuit board features two NVIDIA chips at its center with four large yellow components in a row above them.

NVIDIA's Rubin Ultra GPU has undergone a significant design revision, according to reports from Taiwanese media, which claim that Team Green wants to ensure supply chain complexities are minimal with the new generation. NVIDIA's Rubin Ultra Will Not Feature Four Dies On One Package, But Rather On a Single Board NVIDIA operates with a highly aggressive product cadence, and while the firm's official disclosure is to be at an annual cycle, the supply chain partners need to act a lot more quickly, which is why the timeline is shorter for them, likely at eight to ten months. With that, we […]

Read full article at https://wccftech.com/nvidias-rubin-ultra-reportedly-scaled-back-to-dual-die-design-instead-of-the-ambitious-four-die-one-amid-supply-chain-concerns/

NVIDIA Feynman GPU Gets 3D Die-Stacking, Custom HBM, & Next-Gen Rosa CPU

16 March 2026 at 20:32

A presenter on stage with a timeline slide detailing NVIDIA technologies from Blackwell to Feynman, featuring components like 'Blackwell H100Xe' and 'BlueField-5.'

NVIDIA has revealed more details of its next-generation AI Data Center solution, Rosa Feynman, built using 3D Die-Stacking. NVIDIA Goes With 3D Die Stacking & Custom HBM Solution For Its Next-gen Rosa Feynman AI Chips NVIDIA's Feynman GPU architecture was confirmed back at GTC 2025. During the announcement, NVIDIA listed the Feynman GPU with next-gen HBM, Vera CPU, and several other connectivity chips that make up the foundation of the AI data center. Well, this year at GTC 2026, NVIDIA is revealing more information and some big changes. First up, NVIDIA is now confirming that its Feynman GPUs will adopt […]

Read full article at https://wccftech.com/nvidia-feynman-gpu-gets-3d-die-stacking-custom-hbm-next-gen-rosa-cpu/

Rambus Intros Industry’s Fastest HBM4E Memory Controller: 60% Faster Vs HBM4 at 4.1 TB/s Per IC

4 March 2026 at 22:00

A close-up image of Rambus semiconductor chips labeled 'Rambus HBM4E'.

Rambus has announced the development of its fastest HBM controller yet, based on the HBM4E standard, offering up to 16 Gbps transfer speeds per pin. Ready For Next-Gen AI Data Center Superchips, Rambus Intros HBM4E Memory Controller As expected, Rambus has developed the world's fastest HBM4E memory controller, offering a 60% boost over its HBM4 controller with up to 16 Gbps pin speeds (vs 10 Gbps on HBM4) and up to 4.1 TB/s of total bandwidth per module (vs 2.56 GB/s on HBM4). The HBM4E standard will be utilized by NVIDIA's Rubin Ultra GPUs and AMD's MI500 series accelerators. Press […]

Read full article at https://wccftech.com/rambus-hbm4e-memory-controller-60-percent-faster-vs-hbm4-at-4-1-tbps/

❌
❌