NVIDIA Next-Gen R100 “Rubin” GPUs In Q4 2025: TSMC N3, 8 HBM4 Stacks, 3nm Grace CPU
Thursday, May 09, 2024NVIDIA Next-Gen R100 “Rubin” GPUs In Q4 2025: TSMC N3, 8 HBM4 Stacks, 3nm Grace CPU
NVIDIA, a leading player in the GPU market, is expected to mass produce its next-generation Rubin R100 GPUs by Q4 2025. Named after Vera Rubin, an American astronomer who made significant contributions to the understanding of dark matter, these GPUs are set to bring a new level of power efficiency and AI performance.
The Rubin R100 GPUs
The Rubin R100 GPUs will be part of NVIDIA’s R-series lineup. These GPUs are expected to use a 4x reticle design, as compared to the 3.3x of Blackwell, and will be manufactured using the TSMC CoWoS-L packaging technology on the N3 process node.
One of the key focuses for NVIDIA with its next-gen Rubin R100 GPUs will be power efficiency. This focus on power efficiency, coupled with increased AI performance, is set to make the Rubin R100 GPUs a game-changer in the industry.
HBM4 Memory and TSMC 3nm Node
NVIDIA is planning to utilize the next-generation HBM4 DRAM to power its R100 GPUs. The company currently uses the fastest HBM3E memory for its B100 GPUs and is expected to refresh these chips with HBM4 variants when the memory solution gets widely mass-produced in late 2025.
The Rubin R100 GPUs will be manufactured using the TSMC N3 process node. TSMC recently laid out plans for up to 5.5x reticle size chips by 2026, which would feature a 100x100mm substrate and allow for up to 12 HBM sites.
The Grace CPU Upgrade
Alongside the R100 GPUs, NVIDIA is also set to upgrade its Grace CPU for the GR200 Superchip module. The upgraded Grace CPU will be based on TSMC’s 3nm process. Currently, the Grace CPU is built on TSMC’s 5nm process node and packs 72 cores for a total of 144 cores on the Grace Superchip solution.
Conclusion
With the Rubin R100 GPUs and the upgraded Grace CPU, NVIDIA is poised to make significant strides in power efficiency and AI performance. As we look forward to the mass production of these GPUs in Q4 2025, it’s clear that NVIDIA is pushing the boundaries of what’s possible in the GPU market.